Search

The complexity of diagnostic (surgical) pathology has increased substantially over the last decades with respect to histomorphological and molecular profiling. Pathology has steadily expanded its role in tumor diagnostics and beyond from disease entity identification via prognosis estimation to precision therapy prediction. It is therefore not surprising that pathology is among the disciplines in medicine with high expectations in the application of artificial intelligence (AI) or machine learning approaches given their capabilities to analyze complex data in a quantitative and standardized manner to further enhance scope and precision of diagnostics. While an obvious application is the analysis of histological images, recent applications for the analysis of molecular profiling data from different sources and clinical data support the notion that AI will enhance both histopathology and molecular pathology in the future. At the same time, current literature should not be misunderstood in a way that pathologists will likely be replaced by AI applications in the foreseeable future. Although AI will transform pathology in the coming years, recent studies reporting AI algorithms to diagnose cancer or predict certain molecular properties deal with relatively simple diagnostic problems that fall short of the diagnostic complexity pathologists face in clinical routine. Here, we review the pertinent literature of AI methods and their applications to pathology, and put the current achievements and what can be expected in the future in the context of the requirements for research and routine diagnostics.

Brain-age (BA) estimates based on deep learning are increasingly used as neuroimaging biomarker for brain health; however, the underlying neural features have remained unclear. We combined ensembles of convolutional neural networks with Layer-wise Relevance Propagation (LRP) to detect which brain features contribute to BA. Trained on magnetic resonance imaging (MRI) data of a population-based study (n=2637, 18-82 years), our models estimated age accurately based on single and multiple modalities, regionally restricted and whole-brain images (mean absolute errors 3.37-3.86 years). We find that BA estimates capture aging at both small and large-scale changes, revealing gross enlargements of ventricles and subarachnoid spaces, as well as white matter lesions, and atrophies that appear throughout the brain. Divergence from expected aging reflected cardiovascular risk factors and accelerated aging was more pronounced in the frontal lobe. Applying LRP, our study demonstrates how superior deep learning models detect brain-aging in healthy and at-risk individuals throughout adulthood.

The digitisation of public sector ICT is driven by a number of factors: Increased self- service via the Internet, the Internet of Things (IoT), real-time business intelligence and the advent of integrated information systems as the “backbone” of organisational ICT. This is accentuated by the Covid-19 pandemic. The paper presents an implemented university level teaching programme that covers the topics of integrated information systems for the environment described above. The paper also deals with the research question of how to embed such a programme in a conventional, public sector-oriented university course programme. It details the didactic specificities and analyses the feedback from the roll out and the prior knowledge required from students and the changes in other elements of a public administration course programme necessitated by digitisation orientation. It finally summarises the experience made and illustrates the necessity for further research.

Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text. These results have sparked a renewed interest in the anomaly detection problem and led to the introduction of a great variety of new methods. With the emergence of numerous such methods, including approaches based on generative models, one-class classification, and reconstruction, there is a growing need to bring methods of this field into a systematic and unified perspective. In this review we aim to identify the common underlying principles as well as the assumptions that are often made implicitly by various methods. In particular, we draw connections between classic 'shallow' and novel deep approaches and show how this relation might cross-fertilize or extend both directions. We further provide an empirical assessment of major existing methods that is enriched by the use of recent explainability techniques, and present specific worked-through examples together with practical advice. Finally, we outline critical open challenges and identify specific paths for future research in anomaly detection., Comment: 40 pages; accepted for publication in the Proceedings of the IEEE

Adversarial attacks on deep learning models have compromised their performance considerably. As remedies, a number of defense methods were proposed, which however, have been circumvented by newer and more sophisticated attacking strategies. In the midst of this ensuing arms race, the problem of robustness against adversarial attacks still remains a challenging task. This paper proposes a novel, simple yet effective defense strategy where off-manifold adversarial samples are driven towards high density regions of the data generating distribution of the (unknown) target class by the Metropolis-adjusted Langevin algorithm (MALA) with perceptual boundary taken into account. To achieve this task, we introduce a generative model of the conditional distribution of the inputs given labels that can be learned through a supervised Denoising Autoencoder (sDAE) in alignment with a discriminative classifier. Our algorithm, called MALA for DEfense (MALADE), is equipped with significant dispersion—projection is distributed broadly. This prevents white box attacks from accurately aligning the input to create an adversarial sample effectively. MALADE is applicable to any existing classifier, providing robust defense as well as off-manifold sample detection. In our experiments, MALADE exhibited state-of-the-art performance against various elaborate attacking strategies.

In recent years, the use of machine learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising applications is the construction of ML-based force fields (FFs), with the aim to narrow the gap between the accuracy of ab initio methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail, and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.

With the broader and highly successful usage of machine learning in industry and the sciences, there has been a growing demand for Explainable AI. Interpretability and explanation methods for gaining a better understanding about the problem solving abilities and strategies of nonlinear Machine Learning, in particular, deep neural networks, are therefore receiving increased attention. In this work we aim to (1) provide a timely overview of this active emerging field, with a focus on 'post-hoc' explanations, and explain its theoretical foundations, (2) put interpretability algorithms to a test both from a theory and comparative evaluation perspective using extensive simulations, (3) outline best practice aspects i.e. how to best include interpretation methods into the standard usage of machine learning and (4) demonstrate successful usage of explainable AI in a representative selection of application scenarios. Finally, we discuss challenges and possible future directions of this exciting foundational field of machine learning., Comment: 30 pages, 20 figures

It is again a great pleasure to welcome you to the 5th International Winter Conference on Brain-Computer Interface in High1 resort. This is the fifth event of the annual Brain-Computer Interface seasonal conference and it has been a great successful tradition so far.

Background Telemedicine stroke networks are mandatory to provide inter-hospital transfer for mechanical thrombectomy (MT). However, studies on patient selection in daily practice are sparse. Methods Here, we analyzed consecutive patients from 01/2014 to 12/2018 within the supraregional stroke network “Neurovascular Network of Southwest Bavaria” (NEVAS) in terms of diagnoses after consultation, inter-hospital transfer and predictors for performing MT. Degree of disability was rated by the modified Rankin Scale (mRS), good outcome was defined as mRS ≤ 2. Successful reperfusion was assumed when the modified thrombolysis in cerebral infarction (mTICI) was 2b-3. Results Of 5722 telemedicine consultations, in 14.1% inter-hospital transfer was performed, mostly because of large vessel occlusion (LVO) stroke. A total of n = 350 patients with LVO were shipped via NEVAS to our center for MT. While n = 52 recanalized spontaneously, MT-treatment was performed in n = 178 patients. MT-treated patients had more severe strokes according to the median National institute of health stroke scale (NIHSS) (16 vs. 13, p p = 0.026) and arrived significantly earlier in our center (184.5 versus 228.0 min, p p = 0.35) and mortality (32.6% versus 23.5%, p = 0.79) were comparable in MT-treated versus no-MT-treated patients. In patients with middle cerebral artery occlusion in the M1 segment or carotid artery occlusion good outcome was twice as often in the MT-group (21.8% vs. 12.8%, p = 0.184). Independent predictors for performing MT were higher NIHSS (OR 1.096), higher ASPECTS (OR 1.28), and earlier time window (OR 0.99). Conclusion Within a telemedicine network stroke care can successfully be organized as only a minority of patients has to be transferred. Our data provide clinical evidence that all MT-eligible patients should be shipped with the fastest transportation modality as possible.

Fully autonomously driving vehicles are expected to be a widely available technology in the near future. Privately owned cars, which remain parked for the majority of their lifetime, may therefore be capable of driving independently during their usual long parking periods (e.g. their owners working hours). Our analysis aims to focus on the potential of a privately owned shared car concept as transition period between the present usages of privately owned cars towards a transportation paradigm of privately owned shared autonomous vehicles. We propose two methods in the field of reachability analysis to evaluate the impact of such vehicles during parking periods. Our proposed methods are applied to a dataset of parking times of users of a telematics service provider in the Munich area (Germany). We show the impact of time and location dependent effects on the analyzed service coverage, such as business week rush hours or cover age divergence between urban and suburban regions.

Machine learning (ML) is transforming all areas of science. The complex and time-consuming calculations in molecular simulations are particularly suitable for an ML revolution and have already been profoundly affected by the application of existing ML methods. Here we review recent ML methods for molecular simulation, with particular focus on (deep) neural networks for the prediction of quantum-mechanical energies and forces, on coarse-grained molecular dynamics, on the extraction of free energy surfaces and kinetics, and on generative network approaches to sample molecular equilibrium structures and compute thermodynamics. To explain these methods and illustrate open methodological problems, we review some important principles of molecular physics and describe how they can be incorporated into ML structures. Finally, we identify and describe a list of open challenges for the interface between ML and molecular simulation.

Unpaired image-to-image domain translation involves the task of transferring an image in one domain to another domain without having pairs of data for supervision. Several methods have been proposed to address this task using Generative Adversarial Networks (GANs) and cycle consistency constraint enforcing the translated image to be mapped back to the original domain. This way, a Deep Neural Network (DNN) learns mapping such that the input training distribution transferred to the target domain matches the target training distribution. However, not all test images are expected to fall inside the data manifold in the input space where the DNN has learned to perform the mapping very well. Such images can have a poor mapping to the target domain. In this paper, we propose to perform Langevin dynamics, which makes a subtle change in the input space bringing them close to the data manifold, producing benign examples. The effect is significant improvement of the mapped image on the target domain. We also show that the score function estimation by denoising autoencoder (DAE), can practically be replaced with any autoencoding structure, which most image-to-image translation methods contain intrinsically due to the cycle consistency constraint. Thus, no additional training is required. We show advantages of our approach for several state-of-the-art image-to-image domain translation models. Quantitative evaluation shows that our proposed method leads to a substantial increase in the accuracy to the target label on multiple state-of-the-art image classifiers, while qualitative user study proves that our method better represents the target domain, achieving better human preference scores.

We apply the vision transformer, a deep machine learning model build around the attention mechanism, on mel-spectrogram representations of raw audio recordings. When adding mel-based data augmentation techniques and sample-weighting, we achieve comparable performance on both (PRS and CCS challenge) tasks of ComParE21, outperforming most single model baselines. We further introduce overlapping vertical patching and evaluate the influence of parameter configurations. Index Terms: audio classification, attention, mel-spectrogram, unbalanced data-sets, computational paralinguistics

Synchronization between oscillatory signals is considered to be one of the main mechanisms through which neuronal populations interact with each other. It is conventionally studied with mass-bivariate measures utilizing either sensor-to-sensor or voxel-to-voxel signals. However, none of these approaches aims at maximizing syn-chronization, especially when two multichannel datasets are present. Examples include cortico-muscular coherence (CMC), cortico-subcortical interactions or hyperscanning (where electroencephalographic EEG/magnetoencephalographic MEG activity is recorded simultaneously from two or more subjects). For all of these cases, a method which could find two spatial projections maximizing the strength of synchronization would be desirable. Here we present such method for the maximization of coherence between two sets of EEG/MEG/EMG(electromyographic)/LFP (localfield potential) recordings. We refer to it as canonical Coherence (caCOH). caCOH maximizes the absolute value of the coherence between the two multivariate spaces in the frequency domain. Thisallows very fast optimization for many frequency bins. Apart from presenting details of the caCOH algorithm, we test its efficacy with simulations using realistic head modelling and focus on the application of caCOH to the detection of cortico-muscular coherence. For this, we used diverse multichannel EEG and EMG recordings and demonstrate the ability of caCOH to extract complex patterns of CMC distributed across spatial and frequency domains. Finally, we indicate other scenarios where caCOH can be used for the extraction of neuronal interactions. C.V. was supported by the Spanish Ministry of Economy with Grant RyC 2014-15671. G.N. was partially funded by the German Research Foundation (DFG, SFB936 Z3 and TRR169, B4). K.-R.M. work was supported by the German Ministry for Education and Research (BMBF) under Grants 01IS14013A-E, 01GQ1115 and 01GQ0850; the German Research Foundation (DFG) under Grant Math+, EXC 2046/1, Project ID 390685689 and by the Institute for Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (No. 2017-0-00451, No. 2017-0-01779). T.W.B. was supported by a Future Fellowship from the Australian Research Council (FT180100622). V.V.N. was partially supported by the Center for Bioelectric Interfaces NRU HSE, RF Government grant, ag. No. 14.641.31.0003. The authors thank Katherina von Carlowitz-Ghori for her support with rCMC code and results.

Demand response (DR) can compensate for imbalances in variable renewable energy supplies. This possibility is particularly interesting for electrochemical processes, due to their high energy intensity. To determine the technical feasibility and economic viability of DR, we chose the chlor‐alkali process with subsequent polyvinyl chloride production, including intermediate storage for ethylene dichloride. We estimate the maximum possible cost savings of implementing load flexibility measures. A process model is set up to determine the system characteristic. Subsequent optimizations result in the facility's best possible dispatch depending on additional and minimum power load, storage volume, and cost of a load change. Real plant data are used to specify model parameters and validate the system characteristic and the plant dispatch. An economic evaluation reveals the economic advantages of efficiency and flexibility. The approach can be used to analyze the DR potential of other chlorine value chains or facilities with high electricity demand in general.

An anomalous sound detection (ASD) system detects substantial deviations from the norm and reports the degree of abnormality through an anomaly score. An important application scenario is the detection of malfunctions in factory machinery. Recent approaches train autoencoders on small segments of the sound's time-frequency representation and use the reconstruction error as a measure of abnormality. However, it was recently shown that this approach leads to consistently higher reconstruction errors for the edge frames of the segments. To alleviate this problem, the Interpolation Deep Neural Network (IDNN) predicts the center frame from the remaining context frames. In this work, we propose DRINK - Deep Recurrent INterpolation NetworKs, an extension of the aforementioned IDNN that enables a variable amount of center and context frames. Moreover, we use a Long-Short Term Memory network to explicitly account for the sequential nature of sound as opposed to simple feed-forward neural networks in the original work. We show that under the right setting of context and center frames, our method is able to outperform the IDNN and autoencoder baselines on a dataset of recordings from factory machinery in 13 out of 16 cases.

Deep learning algorithms have revolutionized data science in many fields by greatly improving prediction performances in comparison to conventional approaches. Recently, explainable artificial intelligence (XAI) has emerged as a novel area of research that goes beyond pure prediction improvement. Knowledge embodied in deep learning methodologies is extracted by interpreting their results. We investigate such explanations to explore the genetic architectures of phenotypes in genome-wide association studies. Instead of testing each position in the genome individually, the novel three-step algorithm, called DeepCOMBI, first trains a neural network for the classification of subjects into their respective phenotypes. Second, it explains the classifiers’ decisions by applying layerwise relevance propagation as one example from the pool of XAI techniques. The resulting importance scores are eventually used to determine a subset of most relevant locations for multiple hypothesis testing in the third step. The performance of DeepCOMBI in terms of power and precision is investigated on generated datasets and a 2007 WTCCC study. Verification of the latter is achieved by validating all findings with independent studies published up until 2020. DeepCOMBI is shown to outperform ordinary raw p-value thresholding as well as other baseline methods. Moreover, two novel disease associations (rs10889923 for hypertension and rs4769283 for type 1 diabetes) were identified.

In the analysis of functional Near-Infrared Spectroscopy (fNIRS) signals from real-world scenarios, artifact rejection is essential. However, currently there exists no gold-standard. Although a plenitude of methodological approaches implicitly assume the presence of latent processes in the signals, elaborate Blind-Source-Separation methods have rarely been applied. A reason are challenging characteristics such as Non-instantaneous and non-constant coupling, correlated noise and statistical dependencies between signal components. We present a novel suitable BSS framework that tackles these issues by incorporating A) Independent Component Analysis methods that exploit both higher order statistics and sample dependency, B) multimodality, i.e., fNIRS with accelerometer signals, and C) Canonical-Correlation Analysis with temporal embedding. This enables analysis of signal components and rejection of motion-induced physiological hemodynamic artifacts that would otherwise be hard to identify. We implement a method for Blind Source Separation and Accelerometer based Artifact Rejection and Detection (BLISS A 2 RD). It allows the analysis of a novel n-back based cognitive workload paradigm in freely moving subjects, that is also presented in this manuscript. We evaluate on the corresponding data set and simulated ground truth data, making use of metrics based on 1st and 2nd order statistics and SNR and compare with three established methods: PCA, Spline and Wavelet-based artifact removal. Across 17 subjects, the method is shown to reduce movement induced artifacts by up to two orders of magnitude, improves the SNR of continuous hemodynamic signals in single channels by up to 10 d B , and significantly outperforms conventional methods in the extraction of simulated Hemodynamic Response Functions from strongly contaminated data. The framework and methods presented can serve as an introduction to a new type of multivariate methods for the analysis of fNIRS signals and as a blueprint for artifact rejection in complex environments beyond the applied paradigm.

The PSNR and MSE are the computationally simplest and thus most widely used measures for image quality, although they correlate only poorly with perceived visual quality. More accurate quality models that rely on processing on both the reference and distorted image are potentially difficult to integrate in time-critical communication systems where computational complexity is disadvantageous. This paper derives the concept of distortion sensitivity as a property of the reference image that compensates for a given computational quality model a potential lack of perceptual relevance. This compensation method is applied to the PSNR and leads to a local weighting scheme for the MSE. Local weights are estimated by a deep convolutional neural network and used to improve the PSNR in a computationally graceful distribution of computationally complex processing to the reference image only. The performance of the proposed estimation approach is evaluated on LIVE, TID2013 and CSIQ databases and shows comparable or superior performance compared to benchmark image quality measures.

Many learning tasks in the field of natural language processing including sequence tagging, sequence segmentation, and syntactic parsing have been successfully approached by means of structured prediction methods. An appealing property of the corresponding training algorithms is their ability to integrate the loss function of interest into the optimization process improving the final results according to the chosen measure of performance. Here, we focus on the task of constituency parsing and show how to optimize the model for the $F_{1}$ -score in the max-margin framework of a structural support vector machine (SVM). For reasons of computational efficiency, it is a common approach to binarize the corresponding grammar before training. Unfortunately, this introduces a bias during the training procedure as the corresponding loss function is evaluated on the binary representation, while the resulting performance is measured on the original unbinarized trees. Here, we address this problem by extending the inference procedure presented by Bauer et al. Specifically, we propose an algorithmic modification that allows evaluating the loss on the unbinarized trees. The new approach properly models the loss function of interest resulting in better prediction accuracy and still benefits from the computational efficiency due to binarized representation. The presented idea can be easily transferred to other structured loss functions.

Machine learning is an established and frequently used technique in industry and academia but a standard process model to improve success and efficiency of machine learning applications is still missing. Project organizations and machine learning practitioners have a need for guidance throughout the life cycle of a machine learning application to meet business expectations. We therefore propose a process model for the development of machine learning applications, that covers six phases from defining the scope to maintaining the deployed machine learning application. The first phase combines business and data understanding as data availability oftentimes affects the feasibility of the project. The sixth phase covers state-of-the-art approaches for monitoring and maintenance of a machine learning applications, as the risk of model degradation in a changing environment is eminent. With each task of the process, we propose quality assurance methodology that is suitable to adress challenges in machine learning development that we identify in form of risks. The methodology is drawn from practical experience and scientific literature and has proven to be general and stable. The process model expands on CRISP-DM, a data mining process model that enjoys strong industry support but lacks to address machine learning specific tasks. Our work proposes an industry and application neutral process model tailored for machine learning applications with focus on technical tasks for quality assurance., Machine Learning Applications, Quality Assurance Methodology, Process Model, Best Practices for Machine Learning Applications, Automotive Industry and Academia, Best Practices, Guidelines

Machine learning models are poised to make a transformative impact on chemical sciences by dramatically accelerating computational algorithms and amplifying insights available from computational chemistry methods. However, achieving this requires a confluence and coaction of expertise in computer science and physical sciences. This review is written for new and experienced researchers working at the intersection of both fields. We first provide concise tutorials of computational chemistry and machine learning methods, showing how insights involving both can be achieved. We then follow with a critical review of noteworthy applications that demonstrate how computational chemistry and machine learning can be used together to provide insightful (and useful) predictions in molecular and materials modeling, retrosyntheses, catalysis, and drug design., 169 pages, 24 figures

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the weights of various layers while at the same time aiming to not sacrifice performance. In this paper, we propose a novel criterion for CNN pruning inspired by neural network interpretability: The most relevant units, i.e. weights or filters, are automatically found using their relevance scores obtained from concepts of explainable AI (XAI). By exploring this idea, we connect the lines of interpretability and model compression research. We show that our proposed method can efficiently prune CNN models in transfer-learning setups in which networks pre-trained on large corpora are adapted to specialized tasks. The method is evaluated on a broad range of computer vision datasets. Notably, our novel criterion is not only competitive or better compared to state-of-the-art pruning criteria when successive retraining is performed, but clearly outperforms these previous criteria in the resource-constrained application scenario in which the data of the task to be transferred to is very scarce and one chooses to refrain from fine-tuning. Our method is able to compress the model iteratively while maintaining or even improving accuracy. At the same time, it has a computational cost in the order of gradient computation and is comparatively simple to apply without the need for tuning hyperparameters for pruning., Comment: 25 pages + 5 supplementary pages, 13 figures, 6 tables

In this work, we thoroughly evaluate the efficacy of pretrained neural networks as feature extractors for anomalous sound detection. In doing so, we leverage the knowledge that is contained in these neural networks to extract semantically rich features (representations) that serve as input to a Gaussian Mixture Model which is used as a density estimator to model normality. We compare feature extractors that were trained on data from various domains, namely: images, environmental sounds and music. Our approach is evaluated on recordings from factory machinery such as valves, pumps, sliders and fans. All of the evaluated representations outperform the autoencoder baseline with music based representations yielding the best performance in most cases. These results challenge the common assumption that closely matching the domain of the feature extractor and the downstream task results in better downstream task performance., ICAART 2021, 10 pages, 7 figures, 2 tables

In many fields of research, labeled datasets are hard to acquire. This is where data augmentation promises to overcome the lack of training data in the context of neural network engineering and classification tasks. The idea here is to reduce model over-fitting to the feature distribution of a small under-descriptive training dataset. We try to evaluate such data augmentation techniques to gather insights in the performance boost they provide for several convolutional neural networks on mel-spectrogram representations of audio data. We show the impact of data augmentation on the binary classification task of surgical mask detection in samples of human voice (ComParE Challenge 2020). Also we consider four varying architectures to account for augmentation robustness. Results show that most of the baselines given by ComParE are outperformed., Comment: 5 pages, 2 figures, 2 tables

This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in J. Chem. Phys. 153, 124109 (2020) and may be found at https://doi.org/10.1063/5.0023005., Modern machine learning force fields (ML-FF) are able to yield energy and force predictions at the accuracy of high-level ab initio methods, but at a much lower computational cost. On the other hand, classical molecular mechanics force fields (MM-FF) employ fixed functional forms and tend to be less accurate, but considerably faster and transferable between molecules of the same class. In this work, we investigate how both approaches can complement each other. We contrast the ability of ML-FF for reconstructing dynamic and thermodynamic observables to MM-FFs in order to gain a qualitative understanding of the differences between the two approaches. This analysis enables us to modify the generalized AMBER force field by reparametrizing short-range and bonded interactions with more expressive terms to make them more accurate, without sacrificing the key properties that make MM-FFs so successful.

Psychophysiological methods gained a lot of interest in recent years as a potential remedy for the inherent flaws of overt psychophysical quality assessment methods. Among the psychophysiological monitoring methods, electroencephalography showed to be a promising choice. Specifically, the steady state visually evoked potential (SSVEP) was shown to provide a reliable neural correlate of perceived visual quality for degraded texture image patches. This paper evaluates the feasibility of the SSVEP-based quality assessment approach for more realistic and practically relevant images. To this end, we collected overt, psychophysical responses and neural, psychophysiological responses of 14 participants to 6 HD images each compressed at 4 distortion levels. The psychophysical part followed the Degradation Category Rating procedure. In the subsequent psychophysiological part, the subjects were presented with distorted and reference images alternating at a fixed rate of $f_{stim}\,=5$ Hz to elicit the SSVEP. We show that the amplitude of the $1 ^{st}$ harmonic of the SSVEP correlates significantly with the psychophysical responses $(\vert \rho \vert = 0.85, p \lt 0.05)$ in a single channel analysis at the Oz electrode.

Many learning algorithms such as kernel machines, nearest neighbors, clustering, or anomaly detection, are based on the concept of 'distance' or 'similarity'. Before similarities are used for training an actual machine learning model, we would like to verify that they are bound to meaningful patterns in the data. In this paper, we propose to make similarities interpretable by augmenting them with an explanation in terms of input features. We develop BiLRP, a scalable and theoretically founded method to systematically decompose similarity scores on pairs of input features. Our method can be expressed as a composition of LRP explanations, which were shown in previous works to scale to highly nonlinear functions. Through an extensive set of experiments, we demonstrate that BiLRP robustly explains complex similarity models, e.g. built on VGG-16 deep neural network features. Additionally, we apply our method to an open problem in digital humanities: detailed assessment of similarity between historical documents such as astronomical tables. Here again, BiLRP provides insight and brings verifiability into a highly engineered and problem-specific similarity model., Comment: 12 pages, 10 figures

Previous studies have shown the superior performance of hybrid electroencephalography (EEG)/ near-infrared spectroscopy (NIRS) brain-computer interfaces (BCIs). However, it has been veiled whether the use of a hybrid EEG/NIRS modality can provide better performance for a brain switch that can detect the onset of the intention to turn on a BCI. In this study, we developed such a hybrid EEG/NIRS brain switch and compared its performance with single modality EEG- and NIRS-based brain switch respectively, in terms of true positive rate (TPR), false positive rate (FPR), onset detection time (ODT), and information transfer rate (ITR). In an offline analysis, the performance of a hybrid EEG/NIRS brain switch was significantly improved over that of EEG- and NIRS-based brain switches in general, and in particular a significantly lower FPR was observed for the hybrid EEG/NIRS brain switch. A pseudo-online analysis was additionally performed to confirm the feasibility of implementing an online BCI system with our hybrid EEG/NIRS brain switch. The overall trend of pseudo-online analysis results generally coincided with that of the offline analysis results. No significant difference in all performance measures was also found between offline and pseudo online analysis schemes when the amount of training data was same, with one exception for the ITRs of an EEG brain switch. These offline and pseudo-online results demonstrate that a hybrid EEG/NIRS brain switch can be used to provide a better onset detection performance than that of a single neuroimaging modality.

Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it’s popularity, it has been observed that Federated Learning yields suboptimal results if the local clients’ data distributions diverge. The recently proposed Clustered Federated Learning Framework addresses this issue, by separating the client population into different groups based on the pairwise cosine similarities between their parameter updates. In this work we investigate the application of CFL to byzantine settings, where a subset of clients behaves unpredictably or tries to disturb the joint training effort in an directed or undirected way. We perform experiments with deep neural networks on common Federated Learning datasets which demonstrate that CFL (without modifications) is able to reliably detect byzantine clients and remove them from training.

For the robust estimation of evoked brain activity from functional Near-Infrared Spectroscopy (fNIRS) signals, it is crucial to reduce nuisance signals from systemic physiology and motion. The current best practice incorporates short-separation (SS) fNIRS measurements as regressors in a General Linear Model (GLM). However, several challenging signal characteristics such as non-instantaneous and non-constant coupling are not yet addressed by this approach and additional auxiliary signals are not optimally exploited. We have recently introduced a new methodological framework for the unsupervised multivariate analysis of fNIRS signals using Blind Source Separation (BSS) methods. Building onto the framework, in this manuscript we show how to incorporate the advantages of regularized temporally embedded Canonical Correlation Analysis (tCCA) into the supervised GLM. This approach allows flexible integration of any number of auxiliary modalities and signals. We provide guidance for the selection of optimal parameters and auxiliary signals for the proposed GLM extension. Its performance in the recovery of evoked HRFs is then evaluated using both simulated ground truth data and real experimental data and compared with the GLM with short-separation regression. Our results show that the GLM with tCCA significantly improves upon the current best practice, yielding significantly better results across all applied metrics: Correlation (HbO max. +45%), Root Mean Squared Error (HbO max. −55%), F-Score (HbO up to 3.25-fold) and p-value as well as power spectral density of the noise floor. The proposed method can be incorporated into the GLM in an easily applicable way that flexibly combines any available auxiliary signals into optimal nuisance regressors. This work has potential significance both for conventional neuroscientific fNIRS experiments as well as for emerging applications of fNIRS in everyday environments, medicine and BCI, where high Contrast to Noise Ratio is of importance for single trial analysis.

Cellular imaging with confocal fluorescence laser microscopy gave rise to many new insights into the cellular machinery. One interesting observation suggests that morphology of cell nucleus plays a key role for neutrophilic function, which is an essential part of the innate immune system of most mammals. Due to the increasing availability of high resolution 3D images coming from the microscope, machine learning becomes a promising tool for automatically discovering underlying hidden structures. Here, the major difficulty consists of selecting an appropriate representation for characterizing the morphology of cell nucleus. In this work we tackle this problem and propose a fully unsupervised mechanism for finding structure in high-throughput 3D image data. The key component of our approach is based on Generic Fourier Transform (GFT) for 2D images, which for 3D involves spherical coordinate transformation prior to fast Discrete Fourier Transformation. On top on GFT we apply dimensionality reduction with Principal Component Analysis, followed by generative cluster analysis with a Gaussian Mixture Model. We validate our new approach first on a synthetic 3D-MNIST dataset with random rotations, where quantitative and qualitative results confirm the applicability of the proposed pipeline for exploring shape space in a purely unsupervised manner. Then we apply our proposed technique to a new collected dataset of high resolution 3D images of neutrophile nuclei suggesting a clustering model with six significant clusters of morphological cell nuclei prototypes. We visualize differences in the cell shape clusters by providing prototypical examples of neutrophilic cell nuclei.

In this work we present STEVE - Soccer TEam VEctors, a principled approach for learning real valued vectors for soccer teams where similar teams are close to each other in the resulting vector space. STEVE only relies on freely available information about the matches teams played in the past. These vectors can serve as input to various machine learning tasks. Evaluating on the task of team market value estimation, STEVE outperforms all its competitors. Moreover, we use STEVE for similarity search and to rank soccer teams .

One critical prerequisite for the deployment of reinforcement learning systems in the real world is the ability to reliably detect situations on which the agent was not trained. Such situations could lead to potential safety risks when wrong predictions lead to the execution of harmful actions. In this work, we propose PEOC, a new policy entropy based out-of-distribution classifier that reliably detects unencountered states in deep reinforcement learning. It is based on using the entropy of an agent’s policy as the classification score of a one-class classifier. We evaluate our approach using a procedural environment generator. Results show that PEOC is highly competitive against state-of-the-art one-class classification algorithms on the evaluated environments. Furthermore, we present a structured process for benchmarking out-of-distribution classification in reinforcement learning.

Deep learning has recently gained popularity in digital pathology due to its high prediction quality. However, the medical domain requires explanation and insight for a better understanding beyond standard quantitative performance evaluation. Recently, explanation methods have emerged, which are so far still rarely used in medicine. This work shows their application to generate heatmaps that allow to resolve common challenges encountered in deep learning-based digital histopathology analyses. These challenges comprise biases typically inherent to histopathology data. We study binary classification tasks of tumor tissue discrimination in publicly available haematoxylin and eosin slides of various tumor entities and investigate three types of biases: (1) biases which affect the entire dataset, (2) biases which are by chance correlated with class labels and (3) sampling biases. While standard analyses focus on patch-level evaluation, we advocate pixel-wise heatmaps, which offer a more precise and versatile diagnostic instrument and furthermore help to reveal biases in the data. This insight is shown to not only detect but also to be helpful to remove the effects of common hidden biases, which improves generalization within and across datasets. For example, we could see a trend of improved area under the receiver operating characteristic curve by 5% when reducing a labeling bias. Explanation techniques are thus demonstrated to be a helpful and highly relevant tool for the development and the deployment phases within the life cycle of real-world applications in digital pathology.

We develop a combined machine learning (ML) and quantum mechanics approach that enables data-efficient reconstruction of flexible molecular force fields from high-level ab initio calculations, through the consideration of fundamental physical constraints. We discuss how such constraints are recovered and incorporated into ML models. Specifically, we use conservation of energy—a fundamental property of closed classical and quantum mechanical systems—to derive an efficient gradient-domain machine learning (GDML) model. The challenge of constructing conservative force fields is accomplished by learning in a Hilbert space of vector-valued functions that obey the law of energy conservation. We proceed with the development of a multi-partite matching algorithm that enables a fully automated recovery of physically relevant point group and fluxional symmetries from the training dataset into a symmetric variant of our model. The symmetric GDML (sGDML) approach is able to faithfully reproduce global force fields at the accuracy high-level ab initio methods, thus enabling sample intensive tasks like molecular dynamics simulations at that level of accuracy. (This chapter is adapted with permission from Chmiela (Towards exact molecular dynamics simulations with invariant machine-learned models, PhD thesis. Technische Universitat, Berlin, 2019).)

Federated learning allows multiple parties to jointly train a deep learning model on their combined data, without any of the participants having to reveal their local data to a centralized server. This form of privacy-preserving collaborative learning, however, comes at the cost of a significant communication overhead during training. To address this problem, several compression methods have been proposed in the distributed training literature that can reduce the amount of required communication by up to three orders of magnitude. These existing methods, however, are only of limited utility in the federated learning setting, as they either only compress the upstream communication from the clients to the server (leaving the downstream communication uncompressed) or only perform well under idealized conditions, such as i.i.d. distribution of the client data, which typically cannot be found in federated learning. In this article, we propose sparse ternary compression (STC), a new compression framework that is specifically designed to meet the requirements of the federated learning environment. STC extends the existing compression technique of top- $k$ gradient sparsification with a novel mechanism to enable downstream compression as well as ternarization and optimal Golomb encoding of the weight updates. Our experiments on four different learning tasks demonstrate that STC distinctively outperforms federated averaging in common federated learning scenarios. These results advocate for a paradigm shift in federated optimization toward high-frequency low-bitwidth communication, in particular in the bandwidth-constrained learning environments.

The eligibility for hormone therapy to treat breast cancer largely depends on the tumor’s estrogen receptor (ER) status. Recent studies show that the ER status correlates with morphological features found in Haematoxylin-Eosin (HE) slides. Thus, HE analysis might be sufficient for patients for whom the classifier confidently predicts the ER status and thereby obviate the need for additional examination, such as immunohistochemical (IHC) staining. Several prior works are limited by either the use of engineered features, multi-stage models that use features unspecific to HE images or a lack of explainability. To address these limitations, this work proposes an end-to-end neural network ensemble that shows state-of-the-art performance. We demonstrate that the approach also translates to the prediction of the cancer grade. Moreover, subsets can be selected from the test data for which the model can detect a positive ER status with a precision of 94% while classifying 13% of the patients. To compensate for the reduced interpretability of the model that comes along with end-to-end training, this work applies Layer-wise Relevance Propagation (LRP) to determine the relevant parts of the images a posteriori, commonly visualized as a heatmap overlayed with the input image. We found that nuclear and stromal morphology and lymphocyte infiltration play an important role in the classification of the ER status. This demonstrates that interpretable machine learning can be a vital tool for validating and generating hypotheses about morphological biomarkers.

The service quality and system dependability of real-time communication networks strongly depends on the analysis of monitored data, to identify concrete problems and their causes. Many of these can be described by either their structural or temporal properties, or a combination of both. As current research is short of approaches sufficiently addressing both properties simultaneously, we propose a new feature space specifically suited for this task, which we analyze for its theoretical properties and its practical relevance. We evaluate its classification performance when used on real-world data sets of structural-temporal mobile communication data, and compare it to the performance achieved of feature representations used in related work. For this purpose we propose a system which allows the automatic detection and prediction of classes of pre-defined sequence behavior, greatly reducing costs caused by the otherwise required manual analysis. With our proposed feature spaces this system achieves a precision of more than 93% at recall values of 100%, with an up to 6.7% higher effective recall than otherwise similarly performing alternatives, notably outperforming alternative deep learning, kernel learning and ensemble learning approaches of related work. Furthermore the supported system calibration allows separating reliable from unreliable predictions more effectively, which is highly relevant for any practical application.

This paper applies reinforcement learning to train a predator to hunt multiple prey, which are able to reproduce, in a 2D simulation. It is shown that, using methods of curriculum learning, long-te...

In industrial applications, the early detection of malfunctioning factory machinery is crucial. In this paper, we consider acoustic malfunction detection via transfer learning. Contrary to the majority of current approaches which are based on deep autoencoders, we propose to extract features using neural networks that were pretrained on the task of image classification. We then use these features to train a variety of anomaly detection models and show that this improves results compared to convolutional autoencoders in recordings of four different factory machines in noisy environments. Moreover, we find that features extracted from ResNet based networks yield better results than those from AlexNet and Squeezenet. In our setting, Gaussian Mixture Models and One-Class Support Vector Machines achieve the best anomaly detection performance., Comment: ICAART 2021, 8 pages, 2 figures, 1 table

The difficulty of mountainbike downhill trails is a subjective perception. However, sports-associations and mountainbike park operators attempt to group trails into different levels of difficulty with scales like the Singletrail-Skala (S0-S5) or colored scales (blue, red, black, ...) as proposed by The International Mountain Bicycling Association. Inconsistencies in difficulty grading occur due to the various scales, different people grading the trails, differences in topography, and more. We propose an end-to-end deep learning approach to classify trails into three difficulties easy, medium, and hard by using sensor data. With mbientlab Meta Motion r0.2 sensor units, we record accelerometer- and gyroscope data of one rider on multiple trail segments. A 2D convolutional neural network is trained with a stacked and concatenated representation of the aforementioned data as its input. We run experiments with five different sample- and five different kernel sizes and achieve a maximum Sparse Categorical Accuracy of 0.9097. To the best of our knowledge, this is the first work targeting computational difficulty classification of mountainbike downhill trails.

Kernel ridge regression (KRR) is one of the most popular methods of non-linear regression analysis in quantum chemistry. One of the main ingredients of KRR is the representation of the underlying physical system which mainly determines the performance of predicting quantum-mechanical properties based on KRR. Several such representations have been developed for both, solids and molecules; all of them with different advantages and limitations. These descriptors correspond to a similarity measure between two chemical compounds which is represented by the kernel. As recent approaches define the kernel directly from the underlying physical system, it is important to understand the properties of kernels and how these kernel properties can be used to improve the performance of machine learning models for quantum chemistry. After reviewing key representations of molecules, we provide an intuition on how the choice of the kernel affects the model. This is followed by a more practical guide of two complementary kernel methods, one for supervised and one for unsupervised learning, respectively. Finally, we present a way to gain an understanding about the model complexity by estimating the effective dimensionality induced by the data, the representation, and the kernel.

Explanation methods shed light on the decision process of black-box classifiers such as deep neural networks. But their usefulness can be compromised because they are susceptible to manipulations. With this work, we aim to enhance the resilience of explanations. We develop a unified theoretical framework for deriving bounds on the maximal manipulability of a model. Based on these theoretical insights, we present three different techniques to boost robustness against manipulation: training with weight decay, smoothing activation functions, and minimizing the Hessian of the network. Our experimental results confirm the effectiveness of these approaches.

The extent of tumor-infiltrating lymphocytes (TILs), along with immunomodulatory ligands, tumor-mutational burden and other biomarkers, has been demonstrated to be a marker of response to immune-checkpoint therapy in several cancers. Pathologists have therefore started to devise standardized visual approaches to quantify TILs for therapy prediction. However, despite successful standardization efforts visual TIL estimation is slow, with limited precision and lacks the ability to evaluate more complex properties such as TIL distribution patterns. Therefore, computational image analysis approaches are needed to provide standardized and efficient TIL quantification. Here, we discuss different automated TIL scoring approaches ranging from classical image segmentation, where cell boundaries are identified and the resulting objects classified according to shape properties, to machine learning-based approaches that directly classify cells without segmentation but rely on large amounts of training data. In contrast to conventional machine learning (ML) approaches that are often criticized for their “black-box” characteristics, we also discuss explainable machine learning. Such approaches render ML results interpretable and explain the computational decision-making process through high-resolution heatmaps that highlight TILs and cancer cells and therefore allow for quantification and plausibility checks in biomedical research and diagnostics., SCOPUS: re.j, info:eu-repo/semantics/published

Rational design of compounds with specific properties requires understanding and fast evaluation of molecular properties throughout chemical compound space — the huge set of all potentially stable molecules. Recent advances in combining quantum-mechanical calculations with machine learning provide powerful tools for exploring wide swathes of chemical compound space. We present our perspective on this exciting and quickly developing field by discussing key advances in the development and applications of quantum-mechanics-based machine-learning methods to diverse compounds and properties, and outlining the challenges ahead. We argue that significant progress in the exploration and understanding of chemical compound space can be made through a systematic combination of rigorous physical theories, comprehensive synthetic data sets of microscopic and macroscopic properties, and modern machine-learning methods that account for physical and chemical knowledge. Machine-learning techniques have enabled, among many other applications, the exploration of molecular properties throughout chemical space. The specific development of quantum-based approaches in machine learning can now help us unravel new chemical insights.

Machine learning advances chemistry and materials science by enabling large-scale exploration of chemical space based on quantum chemical calculations. While these models supply fast and accurate predictions of atomistic chemical properties, they do not explicitly capture the electronic degrees of freedom of a molecule, which limits their applicability for reactive chemistry and chemical analysis. Here we present a deep learning framework for the prediction of the quantum mechanical wavefunction in a local basis of atomic orbitals from which all other ground-state properties can be derived. This approach retains full access to the electronic structure via the wavefunction at force-field-like efficiency and captures quantum mechanics in an analytically differentiable representation. On several examples, we demonstrate that this opens promising avenues to perform inverse design of molecular structures for targeting electronic property optimisation and a clear path towards increased synergy of machine learning and quantum chemistry., Machine learning models can accurately predict atomistic chemical properties but do not provide access to the molecular electronic structure. Here the authors use a deep learning approach to predict the quantum mechanical wavefunction at high efficiency from which other ground-state properties can be derived.

SchNetPack is a toolbox for the development and application of deep neural networks that predict potential energy surfaces and other quantum-chemical properties of molecules and materials. It contains basic building blocks of atomistic neural networks, manages their training, and provides simple access to common benchmark datasets. This allows for an easy implementation and evaluation of new models. For now, SchNetPack includes implementations of (weighted) atom-centered symmetry functions and the deep tensor neural network SchNet, as well as ready-to-use scripts that allow one to train these models on molecule and material datasets. Based on the PyTorch deep learning framework, SchNetPack allows one to efficiently apply the neural networks to large datasets with millions of reference calculations, as well as parallelize the model across multiple GPUs. Finally, SchNetPack provides an interface to the Atomic Simulation Environment in order to make trained models easily accessible to researchers that are not yet familiar with neural networks.

Most of the fire brigades in Baden-Württemberg are volunteer forces, hence creating the need for readily available and reliable alerting and communication systems for these forces as well. Digital Pagers are the standard means of alerting but, due to their limited reliability, alternative and complementary methods like Apps, SMS, etc. are also used by these volunteer forces. Regarding communication at the scene, the transition from open analogue to encrypted digital radio systems has been on its way for nearly 20 years. As of today, new technology is available for police forces whilst fire brigades still have to use analogue systems. This contribution analyses the situation, past and present, planning and attempts at improvement.