Search

Handling sparse and unstructured geometric data, such as point clouds or event-based vision, is a pressing challenge in the field of machine vision. Recently, sequence models such as Transformers and state-space models entered the domain of geometric data. These methods require specialized preprocessing to create a sequential view of a set of points. Furthermore, prior works involving sequence models iterate geometric data with either uniform or learned step sizes, implicitly relying on the model to infer the underlying geometric structure. In this work, we propose to encode geometric structure explicitly into the parameterization of a state-space model. State-space models are based on linear dynamics governed by a one-dimensional variable such as time or a spatial coordinate. We exploit this dynamic variable to inject relative differences of coordinates into the step size of the state-space model. The resulting geometric operation computes interactions between all pairs of N points in O(N) steps. Our model deploys the Mamba selective state-space model with a modified CUDA kernel to efficiently map sparse geometric data to modern hardware. The resulting sequence model, which we call STREAM, achieves competitive results on a range of benchmarks from point-cloud classification to event-based vision and audio classification. STREAM demonstrates a powerful inductive bias for sparse geometric data by improving the PointMamba baseline when trained from scratch on the ModelNet40 and ScanObjectNN point cloud analysis datasets. It further achieves, for the first time, 100% test accuracy on all 11 classes of the DVS128 Gestures dataset.

The process industry's high expectations for Digital Twins require modeling approaches that can generalize across tasks and diverse domains with potentially different data dimensions and distributional shifts i.e., Foundational Models. Despite success in natural language processing and computer vision, transfer learning with (self-) supervised signals for pre-training general-purpose models is largely unexplored in the context of Digital Twins in the process industry due to challenges posed by multi-dimensional time-series data, lagged cause-effect dependencies, complex causal structures, and varying number of (exogenous) variables. We propose a novel channel-dependent pre-training strategy that leverages synchronized cause-effect pairs to overcome these challenges by breaking down the multi-dimensional time-series data into pairs of cause-effect variables. Our approach focuses on: (i) identifying highly lagged causal relationships using data-driven methods, (ii) synchronizing cause-effect pairs to generate training samples for channel-dependent pre-training, and (iii) evaluating the effectiveness of this approach in channel-dependent forecasting. Our experimental results demonstrate significant improvements in forecasting accuracy and generalization capability compared to traditional training methods., Comment: 14 pages

Most datasets in the field of document analysis utilize highly standardized labels, which, while simplifying specific tasks, often produce outputs that are not directly applicable to humanities research. In contrast, the Nuremberg Letterbooks dataset, which comprises historical documents from the early 15th century, addresses this gap by providing multiple types of transcriptions and accompanying metadata. This approach allows for developing methods that are more closely aligned with the needs of the humanities. The dataset includes 4 books containing 1711 labeled pages written by 10 scribes. Three types of transcriptions are provided for handwritten text recognition: Basic, diplomatic, and regularized. For the latter two, versions with and without expanded abbreviations are also available. A combination of letter ID and writer ID supports writer identification due to changing writers within pages. In the technical validation, we established baselines for various tasks, demonstrating data consistency and providing benchmarks for future research to build upon.

Language models for biological and chemical sequences enable crucial applications such as drug discovery, protein engineering, and precision medicine. Currently, these language models are predominantly based on Transformer architectures. While Transformers have yielded impressive results, their quadratic runtime dependency on the sequence length complicates their use for long genomic sequences and in-context learning on proteins and chemical sequences. Recently, the recurrent xLSTM architecture has been shown to perform favorably compared to Transformers and modern state-space model (SSM) architectures in the natural language domain. Similar to SSMs, xLSTMs have a linear runtime dependency on the sequence length and allow for constant-memory decoding at inference time, which makes them prime candidates for modeling long-range dependencies in biological and chemical sequences. In this work, we tailor xLSTM towards these domains and propose a suite of architectural variants called Bio-xLSTM. Extensive experiments in three large domains, genomics, proteins, and chemistry, were performed to assess xLSTM's ability to model biological and chemical sequences. The results show that models based on Bio-xLSTM a) can serve as proficient generative models for DNA, protein, and chemical sequences, b) learn rich representations for those modalities, and c) can perform in-context learning for proteins and small molecules.

In this paper, we propose a novel flexible optimization pipeline for determining the optimal adsorption sites, named AUGUR (Aware of Uncertainty Graph Unit Regression). Our model combines graph neural networks and Gaussian processes to create a flexible, efficient, symmetry-aware, translation, and rotation-invariant predictor with inbuilt uncertainty quantification. This predictor is then used as a surrogate for a data-efficient Bayesian Optimization scheme to determine the optimal adsorption positions. This pipeline determines the optimal position of large and complicated clusters with far fewer iterations than current state-of-the-art approaches. Further, it does not rely on hand-crafted features and can be seamlessly employed on any molecule without any alterations. Additionally, the pooling properties of graphs allow for the processing of molecules of different sizes by the same model. This allows the energy prediction of computationally demanding systems by a model trained on comparatively smaller and less expensive ones, Comment: 17 pages 8 figures

A basic fact taught in undergraduate algebra courses is that every finite nilpotent group is a direct product of $p$-groups. Already Bruck observed that this does not generalize to loops. In particular, there exist nilpotent loops of size $6$ which are not direct products of loops of size $2$ and $3$. Still we show that every finite nilpotent loop $(A,\cdot)$ has a binary term operation $*$ such that $(A,*)$ is a direct product of nilpotent loops of prime power order, i.e., $(A,*)$ is supernilpotent. As an application we obtain that every nilpotent loop of order $pq$ for primes $p,q$ has a finite basis for its equational theory.

The imitation of cursive handwriting is mainly limited to generating handwritten words or lines. Multiple synthetic outputs must be stitched together to create paragraphs or whole pages, whereby consistency and layout information are lost. To close this gap, we propose a method for imitating handwriting at the paragraph level that also works for unseen writing styles. Therefore, we introduce a modified latent diffusion model that enriches the encoder-decoder mechanism with specialized loss functions that explicitly preserve the style and content. We enhance the attention mechanism of the diffusion model with adaptive 2D positional encoding and the conditioning mechanism to work with two modalities simultaneously: a style image and the target text. This significantly improves the realism of the generated handwriting. Our approach sets a new benchmark in our comprehensive evaluation. It outperforms all existing imitation methods at both line and paragraph levels, considering combined style and content preservation.

Objective: To explore and compare the performance of ChatGPT and other state-of-the-art LLMs on domain-specific NER tasks covering different entity types and domains in TCM against COVID-19 literature. Methods: We established a dataset of 389 articles on TCM against COVID-19, and manually annotated 48 of them with 6 types of entities belonging to 3 domains as the ground truth, against which the NER performance of LLMs can be assessed. We then performed NER tasks for the 6 entity types using ChatGPT (GPT-3.5 and GPT-4) and 4 state-of-the-art BERT-based question-answering (QA) models (RoBERTa, MiniLM, PubMedBERT and SciBERT) without prior training on the specific task. A domain fine-tuned model (GSAP-NER) was also applied for a comprehensive comparison. Results: The overall performance of LLMs varied significantly in exact match and fuzzy match. In the fuzzy match, ChatGPT surpassed BERT-based QA models in 5 out of 6 tasks, while in exact match, BERT-based QA models outperformed ChatGPT in 5 out of 6 tasks but with a smaller F-1 difference. GPT-4 showed a significant advantage over other models in fuzzy match, especially on the entity type of TCM formula and the Chinese patent drug (TFD) and ingredient (IG). Although GPT-4 outperformed BERT-based models on entity type of herb, target, and research method, none of the F-1 scores exceeded 0.5. GSAP-NER, outperformed GPT-4 in terms of F-1 by a slight margin on RM. ChatGPT achieved considerably higher recalls than precisions, particularly in the fuzzy match. Conclusions: The NER performance of LLMs is highly dependent on the entity type, and their performance varies across application scenarios. ChatGPT could be a good choice for scenarios where high recall is favored. However, for knowledge acquisition in rigorous scenarios, neither ChatGPT nor BERT-based QA models are off-the-shelf tools for professional practitioners., Comment: 22 pages with 2 figures

Confronted with the challenge of identifying the most suitable metric to validate the merits of newly proposed models, the decision-making process is anything but straightforward. Given that comparing rankings introduces its own set of formidable challenges and the likely absence of a universal metric applicable to all scenarios, the scenario does not get any better. Furthermore, metrics designed for specific contexts, such as for Recommender Systems, sometimes extend to other domains without a comprehensive grasp of their underlying mechanisms, resulting in unforeseen outcomes and potential misuses. Complicating matters further, distinct metrics may emphasize different aspects of rankings, frequently leading to seemingly contradictory comparisons of model results and hindering the trustworthiness of evaluations. We unveil these aspects in the domain of ranking evaluation metrics. Firstly, we show instances resulting in inconsistent evaluations, sources of potential mistrust in commonly used metrics; by quantifying the frequency of such disagreements, we prove that these are common in rankings. Afterward, we conceptualize rankings using the mathematical formalism of symmetric groups detaching from possible domains where the metrics have been created; through this approach, we can rigorously and formally establish essential mathematical properties for ranking evaluation metrics, essential for a deeper comprehension of the source of inconsistent evaluations. We conclude with a discussion, connecting our theoretical analysis to the practical applications, highlighting which properties are important in each domain where rankings are commonly evaluated. In conclusion, our analysis sheds light on ranking evaluation metrics, highlighting that inconsistent evaluations should not be seen as a source of mistrust but as the need to carefully choose how to evaluate our models in the future.

Multi-channel electrophysiology systems for recording of neuronal activity face significant data throughput limitations, hampering real-time, data-informed experiments. These limitations impact both experimental neurobiology research and next-generation neuroprosthetics. We present a novel solution that leverages the high integration density of 22nm FDSOI CMOS technology to address these challenges. The proposed highly integrated programmable System-on-Chip comprises 68-channel 0.41 \textmu W/Ch recording frontends, spike detectors, 16-channel 0.87-4.39 \textmu W/Ch action potential and 8-channel 0.32 \textmu W/Ch local field potential codecs, as well as a MAC-assisted power-efficient processor operating at 25 MHz (5.19 \textmu W/MHz). The system supports on-chip training processes for compression, training and inference for neural spike sorting. The spike sorting achieves an average accuracy of 91.48% or 94.12% depending on the utilized features. The proposed PSoC is optimized for reduced area (9 mm2) and power. On-chip processing and compression capabilities free up the data bottlenecks in data transmission (up to 91% space saving ratio), and moreover enable a fully autonomous yet flexible processor-driven operation. Combined, these design considerations overcome data-bottlenecks by allowing on-chip feature extraction and subsequent compression., Comment: 26 pages, 14 figures, 1 table, Journal

The depleted p-channel field effect transistor is the chosen sensor type for the Wide Field Imager of the Athena mission. It will be used in two types of cameras. One will enable observations of a field of view of 40' x 40' by using an array of four 512 x 512 pixel sensors in a 2 x 2 configuration. A second, small one is designed to investigate bright, point-like sources with a time resolution of up to 40 microseconds. Sensors of final size, layout, and technology were fabricated, assembled and characterised. Also, first results from the flight production are available and confirm the excellent performance. In order to be able to estimate the future performance of degraded detectors, a simulation was developed that takes into account the non-analytical threshold effects on the basis of measurement results. We present the measurement analysis and the comparison of simulated and measured values as well as first attempts to use the Monte Carlo simulation to predict performance results based on noise measurements., Comment: SPIE Space Telescopes and Instrumentation 2024: Ultraviolet to Gamma Ray

Central to the digital transformation of the process industry are Digital Twins (DTs), virtual replicas of physical manufacturing systems that combine sensor data with sophisticated data-based or physics-based models, or a combination thereof, to tackle a variety of industrial-relevant tasks like process monitoring, predictive control or decision support. The backbone of a DT, i.e. the concrete modelling methodologies and architectural frameworks supporting these models, are complex, diverse and evolve fast, necessitating a thorough understanding of the latest state-of-the-art methods and trends to stay on top of a highly competitive market. From a research perspective, despite the high research interest in reviewing various aspects of DTs, structured literature reports specifically focusing on unravelling the utilized learning paradigms (e.g. self-supervised learning) for DT-creation in the process industry are a novel contribution in this field. This study aims to address these gaps by (1) systematically analyzing the modelling methodologies (e.g. Convolutional Neural Network, Encoder-Decoder, Hidden Markov Model) and paradigms (e.g. data-driven, physics-based, hybrid) used for DT-creation; (2) assessing the utilized learning strategies (e.g. supervised, unsupervised, self-supervised); (3) analyzing the type of modelling task (e.g. regression, classification, clustering); and (4) identifying the challenges and research gaps, as well as, discuss potential resolutions provided.

Industrial processes generate vast amounts of time series data, yet extracting meaningful relationships and insights remains challenging. This paper introduces a framework for automated knowledge graph learning from time series data, specifically tailored for industrial applications. Our framework addresses the complexities inherent in industrial datasets, transforming them into knowledge graphs that improve decision-making, process optimization, and knowledge discovery. Additionally, it employs Granger causality to identify key attributes that can inform the design of predictive models. To illustrate the practical utility of our approach, we also present a motivating use case demonstrating the benefits of our framework in a real-world industrial scenario. Further, we demonstrate how the automated conversion of time series data into knowledge graphs can identify causal influences or dependencies between important process parameters.

The Wide Field Imager (WFI), one of two instruments on ESA's next large X-ray mission Athena, is designed for imaging spectroscopy of X-rays in the range of 0.2 to 15 keV with a large field of view and high count rate capability. The focal plane consists of back-illuminated DEPFET (Depleted p-channel field effect transistor) sensors that have a high radiation tolerance and provide a near Fano-limited energy resolution. To achieve this, a very low noise readout is required, about 3 electrons ENC at beginning of life is foreseen. This makes the device very susceptible to any radiation induced worsening of the readout noise. The main mechanism of degradation will be the increase of dark current due to displacement damage caused primarily by high energy protons. To study the expected performance degradation, a prototype detector module with fully representative pixel layout and fabrication technology was irradiated with 62.4 MeV protons at the accelerator facility MedAustron in Wiener Neustadt. A total dose equivalent to 3.3 $\textstyle{10^{9}}$ 10-MeV protons/$\mathrm{cm^{2}}$ was applied in two steps. During, in-between and after the irradiations the detector remained at the operating temperature of 213 K and was fully biased and operated. Data was recorded to analyze the signal of all incident particles. We report on the increase of dark current after the irradiation and present the current related damage rate at 213 K. The effect of low temperature annealing at 213 K , 236 K, 253 K, 273 K, and 289 K is presented., Comment: to be published in SPIE Proceeding of Astronomical Telescopes + Instrumentation, 2024

With serial and parallel processors introduced into Spiking Neural Networks (SNNs) execution, more and more researchers are dedicated to improving the performance of the computing paradigms by taking full advantage of the strengths of the available processor. In this paper, we compare and integrate serial and parallel paradigms into one SNN compiling system. For a faster switching between them in the layer granularity, we train the classifier to prejudge a better paradigm before compiling instead of making the decision afterward, saving a great amount of compiling time and RAM space on the host PC. The classifier Adaptive Boost, with the highest accuracy (91.69%) among 12 classifiers, is integrated into the switching system, which utilizes less memory and processors on the multi-core neuromorphic hardware backend SpiNNaker2 than two individual paradigms. To the best of our knowledge, it is the first fast-switching compiling system for SNN simulation.

This study compares and analyses publication and document types in the following bibliographic databases: OpenAlex, Scopus, Web of Science, Semantic Scholar and PubMed. The results demonstrate that typologies can differ considerably between individual database providers. Moreover, the distinction between research and non-research texts, which is required to identify relevant documents for bibliometric analysis, can vary depending on the data source because publications are classified differently in the respective databases. The focus of this study, in addition to the cross-database comparison, is primarily on the coverage and analysis of the publication and document types contained in OpenAlex, as OpenAlex is becoming increasingly important as a free alternative to established proprietary providers for bibliometric analyses at libraries and universities.

The advent of text-image models, most notably CLIP, has significantly transformed the landscape of information retrieval. These models enable the fusion of various modalities, such as text and images. One significant outcome of CLIP is its capability to allow users to search for images using text as a query, as well as vice versa. This is achieved via a joint embedding of images and text data that can, for instance, be used to search for similar items. Despite efficient query processing techniques such as approximate nearest neighbor search, the results may lack precision and completeness. We introduce CLIP-Branches, a novel text-image search engine built upon the CLIP architecture. Our approach enhances traditional text-image search engines by incorporating an interactive fine-tuning phase, which allows the user to further concretize the search query by iteratively defining positive and negative examples. Our framework involves training a classification model given the additional user feedback and essentially outputs all positively classified instances of the entire data catalog. By building upon recent techniques, this inference phase, however, is not implemented by scanning the entire data catalog, but by employing efficient index structures pre-built for the data. Our results show that the fine-tuned results can improve the initial search outputs in terms of relevance and accuracy while maintaining swift response times

We define a congruence that copes with null next-symbol probabilities that arise when the output of a language model is constrained by some means during text generation. We develop an algorithm for efficiently learning the quotient with respect to this congruence and evaluate it on case studies for analyzing statistical properties of LLM., Comment: Workshop Paper

Chronic obstructive pulmonary disease (COPD) is a serious inflammatory lung disease affecting millions of people around the world. Due to an obstructed airflow from the lungs, it also becomes manifest in patients' vocal behaviour. Of particular importance is the detection of an exacerbation episode, which marks an acute phase and often requires hospitalisation and treatment. Previous work has shown that it is possible to distinguish between a pre- and a post-treatment state using automatic analysis of read speech. In this contribution, we examine whether sustained vowels can provide a complementary lens for telling apart these two states. Using a cohort of 50 patients, we show that the inclusion of sustained vowels can improve performance to up to 79\% unweighted average recall, from a 71\% baseline using read speech. We further identify and interpret the most important acoustic features that characterise the manifestation of COPD in sustained vowels., Comment: Accepted to INTERSPEECH 2024

We introduce NeuroSA, a neuromorphic architecture specifically designed to ensure asymptotic convergence to the ground state of an Ising problem using an annealing process that is governed by the physics of quantum mechanical tunneling using Fowler-Nordheim (FN). The core component of NeuroSA consists of a pair of asynchronous ON-OFF neurons, which effectively map classical simulated annealing (SA) dynamics onto a network of integrate-and-fire (IF) neurons. The threshold of each ON-OFF neuron pair is adaptively adjusted by an FN annealer which replicates the optimal escape mechanism and convergence of SA, particularly at low temperatures. To validate the effectiveness of our neuromorphic Ising machine, we systematically solved various benchmark MAX-CUT combinatorial optimization problems. Across multiple runs, NeuroSA consistently generates solutions that approach the state-of-the-art level with high accuracy (greater than 99%), and without any graph-specific hyperparameter tuning. For practical illustration, we present results from an implementation of NeuroSA on the SpiNNaker2 platform, highlighting the feasibility of mapping our proposed architecture onto a standard neuromorphic accelerator platform., Comment: 36 pages, 8 figures

Structured additive distributional copula regression allows to model the joint distribution of multivariate outcomes by relating all distribution parameters to covariates. Estimation via statistical boosting enables accounting for high-dimensional data and incorporating data-driven variable selection, both of which are useful given the complexity of the model class. However, as known from univariate (distributional) regression, the standard boosting algorithm tends to select too many variables with minor importance, particularly in settings with large sample sizes, leading to complex models with difficult interpretation. To counteract this behavior and to avoid selecting base-learners with only a negligible impact, we combined the ideas of probing, stability selection and a new deselection approach with statistical boosting for distributional copula regression. In a simulation study and an application to the joint modelling of weight and length of newborns, we found that all proposed methods enhance variable selection by reducing the number of false positives. However, only stability selection and the deselection approach yielded similar predictive performance to classical boosting. Finally, the deselection approach is better scalable to larger datasets and led to a competitive predictive performance, which we further illustrated in a genomic cohort study from the UK Biobank by modelling the joint genetic predisposition for two phenotypes.

Foehn winds, characterized by abrupt temperature increases and wind speed changes, significantly impact regions on the leeward side of mountain ranges, e.g., by spreading wildfires. Understanding how foehn occurrences change under climate change is crucial. Unfortunately, foehn cannot be measured directly but has to be inferred from meteorological measurements employing suitable classification schemes. Hence, this approach is typically limited to specific periods for which the necessary data are available. We present a novel approach for reconstructing historical foehn occurrences using a combination of unsupervised and supervised probabilistic statistical learning methods. We utilize in-situ measurements (available for recent decades) to train an unsupervised learner (finite mixture model) for automatic foehn classification. These labeled data are then linked to reanalysis data (covering longer periods) using a supervised learner (lasso or boosting). This allows to reconstruct past foehn probabilities based solely on reanalysis data. Applying this method to ERA5 reanalysis data for six stations across Switzerland and Austria achieves accurate hourly reconstructions of north and south foehn occurrence, respectively, dating back to 1940. This paves the way for investigating how seasonal foehn patterns have evolved over the past 83 years, providing valuable insights into climate change impacts on these critical wind events., Comment: Revised version published November 6, 2024: Stauffer, R., Zeileis, A. and Mayr, G. J. (2024), Long-Term Foehn Reconstruction Combining Unsupervised and Supervised Learning. International Journal of Climatology, published November 6 2024, https://doi.org/10.1002/joc.8673

Lablets are autonomous microscopic particles with programmable CMOS electronics that can control electrokinetic phenomena and electrochemical reactions in solution via actuator and sensor microelectrodes. In this paper, we describe the design and fabrication of optimized singulated lablets (CMOS3) with dimensions 140x140x50 micrometers carrying an integrated coplanar encapsulated supercapacitor as a rechargeable power supply. The lablets are designed to allow docking to one another or to a smart surface for interchange of energy, electronic information, and chemicals. The paper focusses on the digital and analog design of the lablets to allow significant programmable functionality in a microscopic footprint, including the control of autonomous actuation and sensing up to the level of being able to support a complete lablet self-reproduction life cycle, although experimentally this remains to be proven. The potential of lablets in autonomous sensing and control and for evolutionary experimentation are discussed., Comment: This article was originally submitted (2016) for review as one of a number of preprints as supporting information for the final review of the EU MICREAgents Project # 318671 (2012-2016). Here it is presented in slightly revised form. The version, v2 contains a reference to the verilog source code on GitHub

Lablets are autonomous microscopic particles with programmable CMOS electronics that canvcontrol electrokinetic phenomena and electrochemical reactions in solution via actuator and sensor microelectrodes. The lablets are designed to be rechargeable using an integrated supercapacitor, and to allow docking to one another or to a smart surface for interchange of energy, electronic information and chemicals. In this paper, we describe the design and fabrication of singulated lablets (CMOS2) at the scale of 100 by 200 {\mu}m, with the supercap adjacent to the functional lablet and occupying half the space. In other works, we have characterized the supercap and described the electronic design and proven functionality using arrays of these lablets. Here we present fabrication details for integrating functional coatings and the supercap and demonstrate electronic functionality of the lablets following singulation., Comment: This article was originally submitted (2016) for review as supporting information for the final review of the EU MICREAgents Project # 318671 (2012-2016). Here it is presented in slightly revised form

Activity and parameter sparsity are two standard methods of making neural networks computationally more efficient. Event-based architectures such as spiking neural networks (SNNs) naturally exhibit activity sparsity, and many methods exist to sparsify their connectivity by pruning weights. While the effect of weight pruning on feed-forward SNNs has been previously studied for computer vision tasks, the effects of pruning for complex sequence tasks like language modeling are less well studied since SNNs have traditionally struggled to achieve meaningful performance on these tasks. Using a recently published SNN-like architecture that works well on small-scale language modeling, we study the effects of weight pruning when combined with activity sparsity. Specifically, we study the trade-off between the multiplicative efficiency gains the combination affords and its effect on task performance for language modeling. To dissect the effects of the two sparsities, we conduct a comparative analysis between densely activated models and sparsely activated event-based models across varying degrees of connectivity sparsity. We demonstrate that sparse activity and sparse connectivity complement each other without a proportional drop in task performance for an event-based neural network trained on the Penn Treebank and WikiText-2 language modeling datasets. Our results suggest sparsely connected event-based neural networks are promising candidates for effective and efficient sequence modeling., Comment: arXiv admin note: text overlap with arXiv:2311.07625

Artificial neural networks (ANNs) have had an enormous impact on a multitude of sectors, from research to industry, generating an unprecedented demand for tailor-suited hardware platforms. Their training and execution is highly memory-intensive, clearly evidencing the limitations affecting the currently available hardware based on the von Neumann architecture, which requires frequent data shuttling due to the physical separation of logic and memory units. This does not only limit the achievable performances but also greatly increases the energy consumption, hindering the integration of ANNs into low-power platforms. New Logic in Memory (LiM) architectures, able to unify memory and logic functionalities into a single component, are highly promising for overcoming these limitations, by drastically reducing the need of data transfers. Recently, it has been shown that a very flexible platform for logic applications can be realized recurring to a multi-gated Schottky-Barrier Field Effect Transistor (SBFET). If equipped with memory capabilities, this architecture could represent an ideal building block for versatile LiM hardware. To reach this goal, here we investigate the integration of a ferroelectric Hf$_{0.5}$Zr$_{0.5}$O$_2$ (HZO) layer onto Dual Top Gated SBFETs. We demonstrate that HZO polarization charges can be successfully employed to tune the height of the two Schottky barriers, influencing the injection behavior, thus defining the transistor mode, switching it between n and p-type transport. The modulation strength is strongly dependent on the polarization pulse height, allowing for the selection of multiple current levels. All these achievable states can be well retained over time, thanks to the HZO stability. The presented result show how ferroelectric-enhanced SBFETs are promising for the realization of novel LiM hardware, enabling low-power circuits for ANNs execution.

Event-based sensors are well suited for real-time processing due to their fast response times and encoding of the sensory data as successive temporal differences. These and other valuable properties, such as a high dynamic range, are suppressed when the data is converted to a frame-based format. However, most current methods either collapse events into frames or cannot scale up when processing the event data directly event-by-event. In this work, we address the key challenges of scaling up event-by-event modeling of the long event streams emitted by such sensors, which is a particularly relevant problem for neuromorphic computing. While prior methods can process up to a few thousand time steps, our model, based on modern recurrent deep state-space models, scales to event streams of millions of events for both training and inference. We leverage their stable parameterization for learning long-range dependencies, parallelizability along the sequence dimension, and their ability to integrate asynchronous events effectively to scale them up to long event streams. We further augment these with novel event-centric techniques enabling our model to match or beat the state-of-the-art performance on several event stream benchmarks. In the Spiking Speech Commands task, we improve state-of-the-art by a large margin of 7.7% to 88.4%. On the DVS128-Gestures dataset, we achieve competitive results without using frames or convolutional neural networks. Our work demonstrates, for the first time, that it is possible to use fully event-based processing with purely recurrent networks to achieve state-of-the-art task performance in several event-based benchmarks.

Let $\mathbf{A}$ be a finite simple non-abelian Mal'cev algebra (e.g. a group, loop, ring). We investigate the Boolean power $\mathbf{D}$ of $\mathbf{A}$ by the countable atomless Boolean algebra $\mathbf{B}$ filtered at some idempotents $e_1,\dots,e_n$ of $\mathbf{A}$. When $e_1,\dots,e_n$ are all idempotents of $\mathbf{A}$ we establish two concrete representations of $\mathbf{D}$: as the Fra\"iss\'e limit of the class of finite direct powers of $\mathbf{A}$, and as congruence classes of the countable free algebra in the variety generated by $\mathbf{A}$. Further, for arbitrary $e_1,\dots,e_n$, we show that $\mathbf{D}$ is $\omega$-categorical and that its automorphism group has the small index property, strong uncountable cofinality and the Bergman property. As necessary background we establish some general properties of congruences and automorphisms of filtered Boolean powers of $\mathbf{A}$ by any Boolean algebra $\mathbf{B}$, including a semidirect decomposition for their automorphism groups.

The study aims to highlight the growth and development of Indo-German collaborative research over the past three decades. Moreover, this study encompasses an in-depth examination of funding acknowledgements to gain valuable insights into the financial support that underpins these collaborative endeavors. Together with this paper, we provide an openly accessible dataset of Indo-German research articles for further and reproducible research activities (the "Indo-German Literature Dataset"). The data were retrieved from the Web of Science (WoS) database from the year 1990 till the 30th of November 2022. A total of 36,999 records were retrieved against the employed query. Acknowledged entities were extracted using a NER model specifically trained for this task. Interrelations between the extracted entities and scientific domains, lengths of acknowledgement texts, number of authors and affiliations, number of citations, and gender of the first author, as well as collaboration patterns between Indian and German funders were examined. The study brings to light that Physics, Chemistry, Materials Science, Astronomy and Astrophysics, and Engineering prominently dominate the Indo-German collaborative research. The United States, followed by England and France, are the most active collaborators in Indian and German research. Additionally, relations between entity, entity type, and scientific domain, were discovered. The study highlights a deeper understanding of the composition of the Indo-German collaborative research landscape of the last 30 years and its significance in advancing scientific knowledge and fostering international partnerships. Furthermore, we provide an open version of the original WoS dataset. The Indo-German Literature Dataset consists of 22,844 articles from OpenAlex and is available for related studies like literature studies and Scientometrics., Comment: 37 pages, 9 figures, accepted paper Global Knowledge, Memory and Communication

We study 2-player concurrent stochastic B\"uchi games on countable graphs. Two players, Max and Min, seek respectively to maximize and minimize the probability of visiting a set of target states infinitely often. We show that there always exist $\varepsilon$-optimal Max strategies that use just a step counter plus 1 bit of public memory. This upper bound holds for all countable graphs, but it is a new result even for the special case of finite graphs. The upper bound is tight in the sense that Max strategies that use just a step counter, or just finite memory, are not sufficient even on finite game graphs. The upper bound is a consequence of a slightly stronger new result: $\varepsilon$-optimal Max strategies for the combined B\"uchi and Transience objective require just 1 bit of public memory (but cannot be memoryless). Our proof techniques also yield a closely related result, that $\varepsilon$-optimal Max strategies for the Transience objective alone (which is only meaningful in infinite graphs) can be memoryless.

We consider finite-state Markov decision processes with the combined Energy-MeanPayoff objective. The controller tries to avoid running out of energy while simultaneously attaining a strictly positive mean payoff in a second dimension. We show that finite memory suffices for almost surely winning strategies for the Energy-MeanPayoff objective. This is in contrast to the closely related Energy-Parity objective, where almost surely winning strategies require infinite memory in general. We show that exponential memory is sufficient (even for deterministic strategies) and necessary (even for randomized strategies) for almost surely winning Energy-MeanPayoff. The upper bound holds even if the strictly positive mean payoff part of the objective is generalized to multidimensional strictly positive mean payoff. Finally, it is decidable in pseudo-polynomial time whether an almost surely winning strategy exists., Comment: Full version (incl. appendix) of a paper presented at ICALP 2024

The recent emergence of deep learning has led to a great deal of work on designing supervised deep semantic segmentation algorithms. As in many tasks sufficient pixel-level labels are very difficult to obtain, we propose a method which combines a Gaussian mixture model (GMM) with unsupervised deep learning techniques. In the standard GMM the pixel values with each sub-region are modelled by a Gaussian distribution. In order to identify the different regions, the parameter vector that minimizes the negative log-likelihood (NLL) function regarding the GMM has to be approximated. For this task, usually iterative optimization methods such as the expectation-maximization (EM) algorithm are used. In this paper, we propose to estimate these parameters directly from the image using a convolutional neural network (CNN). We thus change the iterative procedure in the EM algorithm replacing the expectation-step by a gradient-step with regard to the networks parameters. This means that the network is trained to minimize the NLL function of the GMM which comes with at least two advantages. As once trained, the network is able to predict label probabilities very quickly compared with time consuming iterative optimization methods. Secondly, due to the deep image prior our method is able to partially overcome one of the main disadvantages of GMM, which is not taking into account correlation between neighboring pixels, as it assumes independence between them. We demonstrate the advantages of our method in various experiments on the example of myocardial infarct segmentation on multi-sequence MRI images.

Component-wise gradient boosting algorithms are popular for their intrinsic variable selection and implicit regularization, which can be especially beneficial for very flexible model classes. When estimating generalized additive models for location, scale and shape (GAMLSS) by means of a component-wise gradient boosting algorithm, an important part of the estimation procedure is to determine the relative complexity of the submodels corresponding to the different distribution parameters. Existing methods either suffer from a computationally expensive tuning procedure or can be biased by structural differences in the negative gradients' sizes, which, if encountered, lead to imbalances between the different submodels. Shrunk optimal step lengths have been suggested to replace the typical small fixed step lengths for a non-cyclical boosting algorithm limited to a Gaussian response variable in order to address this issue. In this article, we propose a new adaptive step length approach that accounts for the relative size of the fitted base-learners to ensure a natural balance between the different submodels. The new balanced boosting approach thus represents a computationally efficient and easily generalizable alternative to shrunk optimal step lengths. We implemented the balanced non-cyclical boosting algorithm for a Gaussian, a negative binomial as well as a Weibull distributed response variable and demonstrate the competitive performance of the new adaptive step length approach by means of a simulation study, in the analysis of count data modeling the number of doctor's visits as well as for survival data in an oncological trial., Comment: 34 pages, 26 figures

Being able to identify regions within or around proteins, to which ligands can potentially bind, is an essential step to develop new drugs. Binding site identification methods can now profit from the availability of large amounts of 3D structures in protein structure databases or from AlphaFold predictions. Current binding site identification methods heavily rely on graph neural networks (GNNs), usually designed to output E(3)-equivariant predictions. Such methods turned out to be very beneficial for physics-related tasks like binding energy or motion trajectory prediction. However, the performance of GNNs at binding site identification is still limited potentially due to the lack of dedicated nodes that model hidden geometric entities, such as binding pockets. In this work, we extend E(n)-Equivariant Graph Neural Networks (EGNNs) by adding virtual nodes and applying an extended message passing scheme. The virtual nodes in these graphs are dedicated quantities to learn representations of binding sites, which leads to improved predictive performance. In our experiments, we show that our proposed method VN-EGNN sets a new state-of-the-art at locating binding site centers on COACH420, HOLO4K and PDBbind2020.

In dynamic operational environments, particularly in collaborative robotics, the inevitability of failures necessitates robust and adaptable recovery strategies. Traditional automated recovery strategies, while effective for predefined scenarios, often lack the flexibility required for on-the-fly task management and adaptation to expected failures. Addressing this gap, we propose a novel approach that models recovery behaviors as adaptable robotic skills, leveraging the Behavior Trees and Motion Generators~(BTMG) framework for policy representation. This approach distinguishes itself by employing reinforcement learning~(RL) to dynamically refine recovery behavior parameters, enabling a tailored response to a wide array of failure scenarios with minimal human intervention. We assess our methodology through a series of progressively challenging scenarios within a peg-in-a-hole task, demonstrating the approach's effectiveness in enhancing operational efficiency and task success rates in collaborative robotics settings. We validate our approach using a dual-arm KUKA robot.

This study investigates lightning at tall objects and evaluates the risk of upward lightning (UL) over the eastern Alps and its surrounding areas. While uncommon, UL poses a threat, especially to wind turbines, as the long-duration current of UL can cause significant damage. Current risk assessment methods overlook the impact of meteorological conditions, potentially underestimating UL risks. Therefore, this study employs random forests, a machine learning technique, to analyze the relationship between UL measured at Gaisberg Tower (Austria) and $35$ larger-scale meteorological variables. Of these, the larger-scale upward velocity, wind speed and direction at 10 meters and cloud physics variables contribute most information. The random forests predict the risk of UL across the study area at a 1 km$^2$ resolution. Strong near-surface winds combined with upward deflection by elevated terrain increase UL risk. The diurnal cycle of the UL risk as well as high-risk areas shift seasonally. They are concentrated north/northeast of the Alps in winter due to prevailing northerly winds, and expanding southward, impacting northern Italy in the transitional and summer months. The model performs best in winter, with the highest predicted UL risk coinciding with observed peaks in measured lightning at tall objects. The highest concentration is north of the Alps, where most wind turbines are located, leading to an increase in overall lightning activity. Comprehensive meteorological information is essential for UL risk assessment, as lightning densities are a poor indicator of lightning at tall objects.

Graph neural networks (GNNs), and especially message-passing neural networks, excel in various domains such as physics, drug discovery, and molecular modeling. The expressivity of GNNs with respect to their ability to discriminate non-isomorphic graphs critically depends on the functions employed for message aggregation and graph-level readout. By applying signal propagation theory, we propose a variance-preserving aggregation function (VPA) that maintains expressivity, but yields improved forward and backward dynamics. Experiments demonstrate that VPA leads to increased predictive performance for popular GNN architectures as well as improved learning dynamics. Our results could pave the way towards normalizer-free or self-normalizing GNNs., Comment: Accepted at ICLR 2024 (Tiny Papers Track)

Motivated by challenges in the analysis of biomedical data and observational studies, we develop statistical boosting for the general class of bivariate distributional copula regression with arbitrary marginal distributions, which is suited to model binary, count, continuous or mixed outcomes. In our framework, the joint distribution of arbitrary, bivariate responses is modelled through a parametric copula. To arrive at a model for the entire conditional distribution, not only the marginal distribution parameters but also the copula parameters are related to covariates through additive predictors. We suggest efficient and scalable estimation by means of an adapted component-wise gradient boosting algorithm with statistical models as base-learners. A key benefit of boosting as opposed to classical likelihood or Bayesian estimation is the implicit data-driven variable selection mechanism as well as shrinkage without additional input or assumptions from the analyst. To the best of our knowledge, our implementation is the only one that combines a wide range of covariate effects, marginal distributions, copula functions, and implicit data-driven variable selection. We showcase the versatility of our approach on data from genetic epidemiology, healthcare utilization and childhood undernutrition. Our developments are implemented in the R package gamboostLSS, fostering transparent and reproducible research.