Search

Training an accurate classifier for EEG-based brain-computer interface (BCI) requires EEG data from a large number of users, whereas protecting their data privacy is a critical consideration. Federated learning (FL) is a promising solution to this challenge. This paper proposes Federated classification with local Batch-specific batch normalization and Sharpness-aware minimization (FedBS) for privacy protection in EEG-based motor imagery (MI) classification. FedBS utilizes local batch-specific batch normalization to reduce data discrepancies among different clients, and sharpness-aware minimization optimizer in local training to improve model generalization. Experiments on three public MI datasets using three popular deep learning models demonstrated that FedBS outperformed six state-of-the-art FL approaches. Remarkably, it also outperformed centralized training, which does not consider privacy protection at all. In summary, FedBS protects user EEG data privacy, enabling multiple BCI users to participate in large-scale machine learning model training, which in turn improves the BCI decoding accuracy.

Due to the increasing size of integrated circuits (ICs), their design and optimization phases (i.e., computer-aided design, CAD) grow increasingly complex. At design time, a large design space needs to be explored to find an implementation that fulfills all specifications and then optimizes metrics like energy, area, delay, reliability, etc. At run time, a large configuration space needs to be searched to find the best set of parameters (e.g., voltage/frequency) to further optimize the system. Both spaces are infeasible for exhaustive search typically leading to heuristic optimization algorithms that find some tradeoff between design quality and computational overhead. Machine learning (ML) can build powerful models that have successfully been employed in related domains. In this survey, we categorize how ML may be used and is used for design-time and run-time optimization and exploration strategies of ICs. A metastudy of published techniques unveils areas in CAD that are well explored and underexplored with ML, as well as trends in the employed ML algorithms. We present a comprehensive categorization and summary of the state of the art on ML for CAD. Finally, we summarize the remaining challenges and promising open research directions. [ABSTRACT FROM AUTHOR]

The article reports that With the continued growth of IoT devices and their deployment, manually managing and connecting them is impractical and presents multiple challenges. To that end, Zero Touch Networks that rely on software-based modules instead of dedicated propriety hardware become a viable potential solution. The overall aim of zero-touch networks is for machines to learn how to become more autonomous so that we can delegate complex, mundane tasks to them.

Medicine has entered the digital era, driven by data from new modalities, especially genomics and imaging, as well as new sources such as wearables and Internet of Things. As we gain a deeper understanding of the disease biology and how diseases affect an individual, we are developing targeted therapies to personalize treatments. There is a need for technologies like Artificial Intelligence (AI) to be able to support predictions for personalized treatments. In order to mainstream AI in healthcare we will need to address issues such as explainability, liability and privacy. Developing explainable algorithms and including AI training in medical education are many of the solutions that can help alleviate these concerns. [ABSTRACT FROM AUTHOR]

This special section focuses on the state-of-the-art technologies on parallel and distributed computing techniques for artificial intelligence (AI), machine learning (ML), and deep learning (DL). AI, ML, and DL can enable computers the ability to learn from a large amount of data and use the learned model to optimize a complex problem or discover rules in a complicated system. AI, ML and DL can be applied to push forward the boundaries for many domains and significantly influence our daily life. [ABSTRACT FROM AUTHOR]

Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among the existing techniques, stereo matching remains one of the most widely used in the literature due to its strong connection to the human binocular system. Traditionally, stereo-based depth estimation has been addressed through matching hand-crafted features across multiple images. Despite the extensive amount of research, these traditional techniques still suffer in the presence of highly textured areas, large uniform regions, and occlusions. Motivated by their growing success in solving various 2D and 3D vision problems, deep learning for stereo-based depth estimation has attracted a growing interest from the community, with more than 150 papers published in this area between 2014 and 2019. This new generation of methods has demonstrated a significant leap in performance, enabling applications such as autonomous driving and augmented reality. In this paper, we provide a comprehensive survey of this new and continuously growing field of research, summarize the most commonly used pipelines, and discuss their benefits and limitations. In retrospect of what has been achieved so far, we also conjecture what the future may hold for deep learning-based stereo for depth estimation research. [ABSTRACT FROM AUTHOR]

Heart sound auscultation has been applied in clinical usage for early screening of cardiovascular diseases. Due to the high demand for auscultation expertise, automatic auscultation can help with auxiliary diagnosis and reduce the burden of training professional clinicians. Nevertheless, there is a limit to classic machine learning's performance improvement in the era of Big Data. Deep learning has outperformed classic machine learning in many research fields, as it employs more complex model architectures with a stronger capability of extracting effective representations. Moreover, it has been successfully applied to heart sound analysis in the past years. As most review works about heart sound analysis were carried out before 2017, the present survey is the first to work on a comprehensive overview to summarise papers on heart sound analysis with deep learning published in 2017–2022. This work introduces both classic machine learning and deep learning for comparison, and further offer insights about the advances and future research directions in deep learning for heart sound analysis. [ABSTRACT FROM AUTHOR]

The IEEE Transactions on Semiconductor Manufacturing congratulates Haoyu Yang, Shuhe Li, Wen Chen, Piyush Pathak, Frank Gennari, Ya-Chieh Lai, and Bei Yu whose paper DeePattern: Layout Pattern Generation With Transforming Convolutional Auto-Encoder (Vol. 35, No.1, February 2022) was selected as the Best Paper for 2022 by a team of Associate Editors. This paper proposes generative machine learning models to synthesize VLSI layouts through a pattern generation framework that reduces the challenging creation problem into two simpler subproblems with the aid of an efficient squish pattern representation. The problem is treated by designing an innovative transforming convolutional auto-encoder in TCAE architecture, aiming to generate efficient and representative pattern shapes. The paper introduces a GAN-guided TCAE ML analysis that targets massive DRC-clean and content-specific pattern generation following certain design rules, without losing pattern library diversity. Through experiments on 7nm EUV designs, the authors demonstrate that each latent vector node in TCAE has a real physical meanings in layout domain and transformations on latent vectors can produce additional topologies of interest. Results show that the generated pattern library exhibits larger pattern number and pattern diversity compared to the traditional state-of-the-art industry layout generator. [ABSTRACT FROM AUTHOR]

The papers in this special section present the state-of-the-art technologies and the challenges of parallel and distributed computing techniques for artificial intelligence (AI), machine learning (ML), and deep learning (DL). AI, ML, and DL have established themselves in a multitude of domains because of their ability to process and model unstructured input data. [ABSTRACT FROM AUTHOR]

In this paper, we propose to use commercial off-the-shelf (COTS) monostatic RFID devices (i.e. which use a single antenna at a time for both transmitting and receiving RFID signals to and from the tags) to monitor browsing activity of customers in front of display items in places such as retail stores. To this end, we propose TagSee, a multi-person imaging system based on monostatic RFID imaging. TagSee is based on the insight that when customers are browsing the items on a shelf, they stand between the tags deployed along the boundaries of the shelf and the reader, which changes the multi-paths that the RFID signals travel along, and both the RSS and phase values of the RFID signals that the reader receives change. Based on these variations observed by the reader, TagSee constructs a coarse grained image of the customers. Afterwards, TagSee identifies the items that are being browsed by the customers by analyzing the constructed images. The key novelty of this paper is on achieving browsing behavior monitoring of multiple customers in front of display items by constructing coarse grained images via robust, analytical model-driven deep learning based, RFID imaging. To achieve this, we first mathematically formulate the problem of imaging humans using monostatic RFID devices and derive an approximate analytical imaging model that correlates the variations caused by human obstructions in the RFID signals. Based on this model, we then develop a deep learning framework to robustly image customers with high accuracy. We implement TagSee scheme using a Impinj Speedway R420 reader and SMARTRAC DogBone RFID tags. TagSee can achieve a TPR of more than ${\sim }90\%$ ∼ 90 % and a FPR of less than ${\sim }10\%$ ∼ 10 % in multi-person scenarios using training data from just 3-4 users. [ABSTRACT FROM AUTHOR]

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research. A list of important papers discussed in this survey, corresponding codes, and additional resources on BLOs are publicly available at: https://github.com/vis-opt-group/BLO. [ABSTRACT FROM AUTHOR]

Data quality plays an important role during the training stage of machine/deep learning models. The annotation hinges on the experiences of domain experts. To acquire the expert’s knowledge in the context of machine learning, manual data labeling, a tedious and time-consuming task in supervised learning, should be given a top priority. However, the domain experts in the line of plentiful manual annotation may easily get distracted or fatigued after long-time work, causing judgment errors, mislabeling, etc. The pattern recognition of wafer defect map is investigated in this paper, the primary goal of which is to train the convolutional neural network (CNN) model through a very limited number of manually labeled data so that the trained model is capable of performing pseudo labeling. Subsequently, a self-assured adaptive ensemble learner in terms of a series of shallow neural networks is proposed to filter wafer map samples with untrusted pseudo-labels. In the result, the amount of human annotations is significantly reduced by 61% for training a highly accurate classifier. A minimum number of manually labeled data is suggested while the equally high classification performance of wafer defect pattern is maintained. For the evaluation purpose, the proposed self-assured learning is compared with the confidence learning. [ABSTRACT FROM AUTHOR]

The papers in this special section is to broadly engage the machine learning and multimedia communities on the emerging yet challenging interpretable machine learning. Multimedia is increasingly becoming the "biggest big data," among the most important and valuable source for insight and information. Many powerful machine learning algorithms, especially deep learning models such as convolutional neural networks (CNNs), have recently achieved outstanding predictive performance in a wide range of multimedia applications, including visual object classification, scene understanding, speech recognition, and activity prediction. Nevertheless, most deep learning algorithms are generally conceived as blackbox methods, and it is difficult to intuitively and quantitatively understand the results of their prediction and inference. Since this lack of interpretability is a major bottleneck in designing more successful predictive models and exploring wider-range useful applications, there has been an explosion of interest in interpreting the representations learned by these models, with profound implications for research into interpretable machine learning in the multimedia community. [ABSTRACT FROM AUTHOR]

The papers in this special section focus on increasing interests in the development and implementation of advanced artificial intelligence (AI) and machine learning (ML) methods for tackling the reliability and system health prognostics challenges in various industrial applications. [ABSTRACT FROM AUTHOR]

The ongoing decarbonisation of modern electricity systems has led to a substantial increase of operational uncertainty, particularly due to the large-scale integration of renewable energy generation. However, the expanding space of possible operating points renders necessary the development of novel security assessment approaches. In this paper we focus on the use of security rules where classifiers are trained offline to characterize previously unseen points as safe or unsafe. This paper proposes a novel deep learning-based feature extraction framework for building security rules. We show how deep autoencoders can be used to transform the space of conventional state variables (e.g., power flows) to a small number of dimensions where we can optimally distinguish between safe and unsafe operation. The proposed framework is data-driven and can be useful in multiple applications within the context of security assessment. To achieve high accuracy, a novel objective-based loss function is proposed to address the issue of imbalanced safe/unsafe classes that characterize electricity system operation. Furthermore, an R-vine copula-based model is proposed to sample historical data and generate large populations of anticipated system states for training. The superior performance of the proposed framework is demonstrated through a series of case studies and comparisons using the load and wind generation data from the French transmission system, which have been mapped to the IEEE 118-bus system. [ABSTRACT FROM AUTHOR]

Linear spectral unmixing is the practice of decomposing the mixed pixel into a linear combination of the constituent endmembers and the estimated abundances. This paper focuses on unsupervised spectral unmixing where the endmembers are unknown a priori. Conventional approaches use either geometrical- or statistical-based approaches. In this paper, we address the challenges of spectral unmixing with unsupervised deep learning models, in specific, the autoencoder models, where the decoder serves as the endmembers and the hidden layer output serves as the abundances. In several recent attempts, part-based autoencoders have been designed to solve the unsupervised spectral unmixing problem. However, the performance has not been satisfactory. In this paper, we first discuss some important findings we make on issues with part-based autoencoders. By proof of counterexample, we show that all existing part-based autoencoder networks with nonnegative and tied encoder and decoder are inherently defective by making these inappropriate assumptions on the network structure. As a result, they are not suitable for solving the spectral unmixing problem. We propose a so-called untied denoising autoencoder with sparsity, in which the encoder and decoder of the network are independent, and only the decoder of the network is enforced to be nonnegative. Furthermore, we make two critical additions to the network design. First, since denoising is an essential step for spectral unmixing, we propose to incorporate the denoising capacity into the network optimization in the format of a denoising constraint rather than cascading another denoising preprocessor in order to avoid the introduction of additional reconstruction error. Second, to be more robust to the inaccurate estimation of a number of endmembers, we adopt an $l_{21}$ -norm on the encoder of the network to reduce the redundant endmembers while decreasing the reconstruction error simultaneously. The experimental results demonstrate that the proposed approach outperforms several state-of-the-art methods, especially for highly noisy data. [ABSTRACT FROM AUTHOR]

This paper proposes a smartphone-based Driving Data Recorder (DDR). The proposed DDR has the functions of accurate speed estimation and intelligent traffic scene understanding. DDRs are used to store the relevant driving data to provide feedback on driver behavior for accident analysis, insurance issue, and so on. The conventional DDRs are standalone devices with multiple sensors. The current DDR products record many useless data or lose important information. On the other hand, the widely used smartphones already have the hardware conditions to replace the conventional DDR products. This paper proposes to develop the intelligent DDR in the smartphones. Considering the requirements of the DDRs, two functions are developed in this paper: motion sensor-based speedometer and vision sensor-based scene understanding. The proposed speedometer function adopts double-layered Long Short-Term Memory (LSTM) network as the model, which can estimate the vehicle speed directly from gyroscope and accelerometer of a smartphone. The scene understanding function can detect road facilities such as traffic lights, crosswalks, and stop lines. The driving data recorded in those areas are very important for analyzing driver behaviors. In the development of the scene understanding function, maintaining high detection accuracy with reduced computation cost is significant due to the limitation of smartphones’ processing resources. This paper uses a lightweight architecture deep learning network to achieve the goal. The proposed system has been evaluated using the real traffic data. Speed estimation function only has 1.8 km/h of speed mean error. In addition, there is no accumulated error even for a long time driving. The evaluation of the scene understanding function indicates that the proposed method can provide a high-accuracy detection at 2 FPS, which is faster than the state-of-the-art method. [ABSTRACT FROM AUTHOR]

An editorial is presented on addressing the need for bringing together leading efforts in non-Euclidean deep learning across all communities. Topics include Convolutional Neural Networks (CNNs) relying on classical signal processing models limiting the applicability to data with underlying Euclidean grid-like structure; and multiple levels of abstraction being introduced similarly to multi-layer networks.

As the semiconductor manufacturing process is moving towards the 3 nm node, there is a crucial need to reduce the edge placement error (EPE) to ensure proper functioning of the integrated circuit (IC) devices. EPE is the most important metric that quantify the fidelity of fabricated patterns in multi-patterning processes, and it is the combination of overlay errors and critical dimension (CD) errors. Recent advances in machine learning have enabled many new possibilities to improve the performance and efficiency of EPE optimization techniques. In this paper, we conducted a survey of recent research work that applied machine learning/ deep learning techniques for the purposes of enhancing virtual overlay metrology, reducing overlay error, and improving mask optimization methods for EPE reduction. Thorough discussions about the objectives, datasets, input features, models, key findings, and limitations are provided. In general, the results of the review work show a great potential of machine learning techniques in aiding the improvement of EPE in the field of semiconductor manufacturing. [ABSTRACT FROM AUTHOR]

Detailed routing is one of the most challenging aspects of the physical design process. Many of the violations that occur during the detailed routing stage stem from the placement of the cells. In this paper, we propose a deep learning framework to identify short violations that can occur during detailed routing from a placed netlist. One of the advantages of our technique is that by using the proposed deep learning-based predictor, global routing is no longer required as frequently and hence the total runtime for place and route can be significantly reduced. In this paper, we discuss the proposed framework and the methodology for analyzing the extracted features. The experimental results show that the average sensitivity, specificity, and accuracy of Eh?Predictor is above 90%. In addition, we show that Eh?Predictor is up to 14 times faster than NCTUgr for smaller designs and up to 96 times faster for larger designs. [ABSTRACT FROM AUTHOR]

Recently, data-driven approaches motivated by modern deep learning have been applied to optical communications in place of traditional model-based counterparts. The application of deep neural networks (DNN) allows flexible statistical analysis of complicated fiber-optic systems without relying on any specific physical models. Due to the inherent nonlinearity in DNN, various equalizers based on DNN have shown significant potential to mitigate fiber nonlinearity. In this paper, we propose turbo equalization (TEQ) based on DNN as a new alternative framework to deal with nonlinear fiber impairments. The proposed DNN-TEQ is constructed with nested deep residual networks (ResNet) to train extrinsic likelihood given soft-information feedback from channel decoding. Through extrinsic information transfer (EXIT) analysis, we verify that our DNN-TEQ can accelerate decoding convergence to achieve a significant gain in achievable throughput by 0.61 b/s/Hz. We also demonstrate that optimizing irregular low-density parity-check (LDPC) codes based on the EXIT chart of the DNN-TEQ can improve achievable rates by up to 0.12 b/s/Hz. [ABSTRACT FROM AUTHOR]

Virtual metrology (VM) predicts the actual measurement for ongoing semiconductor process. Optical emission spectroscopy (OES) data is often used to build up VM models, since it has a lot of information on process quality. However, it also includes significant redundant information, so it is important how to select only meaningful features. Deep learning (DL) techniques have been very successful in analyzing image data and it is tempting to apply those techniques to the OES data. In this paper, we propose DL configurations specific to OES data that outperform those used for image analysis. Specifically, our proposed method accounts for variable size data, chamber to chamber differences, condition drift due to accumulation, observation data drift due to an accumulation of deposition on a window, and the effects of maintenance. We evaluated our method on a real, mass-production dataset and compared our results with those obtained by using state-of-the-art image analysis DL techniques in the famous contest, ImageNet large-scale visual recognition challenge (ILSVRC). [ABSTRACT FROM AUTHOR]

The rapid development of Internet technology has brought great convenience to our production life, and the ensuing security problems have become increasingly prominent. These problems threaten users’ privacy and pose significant security risks to the normal conduct of many aspects of society, such as politics, economy, culture, and people’s livelihood. The growth of the information transmission rate expands the scope of attacks and provides a more attack environment for intruders. Abnormal detection is an effective security protection technology that can monitor network transmission in real-time, effectively sense external attacks, and provide response decisions for relevant managers. The development of machine learning has also led to the development of abnormal traffic detection technology. The goal has been to use powerful and fast learning algorithms to deal with changing threats and respond in real-time. Most of the current abnormal detection research is based on simulation, using public and well-known datasets. On the one hand, the dataset contains high-dimensional massive data, which traditional machine learning methods cannot be processed. On the other hand, the labeled data scale is far behind the application requirements, and the dataset’s labels are all manually labeled, so the labeling cost is exceptionally high. This paper proposes a semi-supervised Double Deep Q-Network (SSDDQN)-based optimization method for network abnormal traffic detection, mainly based on Double Deep Q-Network (DDQN), a representative of Deep Reinforcement Learning algorithm. In SSDDQN, the current network first adopts the autoencoder to reconstruct the traffic features and then uses a deep neural network as a classifier. The target network first uses the unsupervised learning algorithm K-Means clustering and then uses deep neural network prediction. The experiment uses NSL-KDD and AWID datasets for training and testing and performs a comprehensive comparison with existing machine learning models. The experimental results show that SSDDQN has certain advantages in time complexity and achieved good results in various evaluation metrics. [ABSTRACT FROM AUTHOR]

As a follow-up to the first IEEE Transactions on Medical Imaging (TMI) special issue on the theme of deep tomographic reconstruction, the second special issue is assembled to reflect the status and momentum of this rapidly emerging field. In this editorial, we provide a brief background illustrating the motivation for the development of network-based, data-driven, and learning-oriented reconstruction methods, summarize the included papers, and report our verification of the shared deep learning codes. Finally, we discuss several important research topics to facilitate further investigation and collaboration. [ABSTRACT FROM AUTHOR]

Thanks to the many submissions we have received, we can present this second part of our special issue on "AI-eXplained." In here, we continue our mission to demystify the intricate world of artificial intelligence and make it accessible to a broader audience. As AI continues to evolve and integrate into various aspects of our lives, it becomes increasingly important to bridge the gap between experts and those eager to understand the inner workings of AI systems. Our goal remains unchanged—to present AI concepts in a comprehensible, engaging, and interactive manner, empowering our readers to explore and grasp the enchanting world of AI. [ABSTRACT FROM AUTHOR]

Electrical capacitance tomography exhibits great potentials in the visualization measurement of industrial processes, and high-precision images are of great significance for the reliability and usefulness of measurement results. In this paper, we propose a deep learning-based inversion method to ameliorate the reconstruction accuracy. With the aid of the deep learning methodology, the prior from the images reconstructed by a certain imaging technique to the true images is abstracted and stored in the deep extreme learning machine. A new cost function is constructed to encapsulate the prior from the proposed deep learning model and the domain expertise about imaging targets, and the split Bregman algorithm and the fast iterative shrinkage thresholding technique are combined into a new numerical method to effectively solve it to get the final reconstruction. The numerical and experimental results validate that the inversion method proposed in this paper reduces the reconstruction artifacts and deformations and leads to the much improvement in the imaging quality. [ABSTRACT FROM AUTHOR]

Time series classification models have been garnering significant importance in the research community. However, not much research has been done on generating adversarial samples for these models. These adversarial samples can become a security concern. In this paper, we propose utilizing an adversarial transformation network (ATN) on a distilled model to attack various time series classification models. The proposed attack on the classification model utilizes a distilled model as a surrogate that mimics the behavior of the attacked classical time series classification models. Our proposed methodology is applied onto 1-nearest neighbor dynamic time warping (1-NN DTW) and a fully convolutional network (FCN), all of which are trained on 42 University of California Riverside (UCR) datasets. In this paper, we show both models were susceptible to attacks on all 42 datasets. When compared to Fast Gradient Sign Method, the proposed attack generates a larger faction of successful adversarial black-box attacks. A simple defense mechanism is successfully devised to reduce the fraction of successful adversarial samples. Finally, we recommend future researchers that develop time series classification models to incorporating adversarial data samples into their training data sets to improve resilience on adversarial samples. [ABSTRACT FROM AUTHOR]

This paper applies machine learning to optimize the transmission policies of cognitive radio inspired non-orthogonal multiple access (CR-NOMA) networks, where time-division multiple access (TDMA) is used to serve multiple primary users and an energy-constrained secondary user is admitted to the primary users’ time slots via NOMA. During each time slot, the secondary user performs the two tasks: data transmission and energy harvesting based on the signals received from the primary users. The goal of the paper is to maximize the secondary user’s long-term throughput, by optimizing its transmit power and the time-sharing coefficient for its two tasks. The long-term throughput maximization problem is challenging due to the need for making decisions that yield long-term gains but might result in short-term losses. For example, when in a given time slot, a primary user with large channel gains transmits, intuition suggests that the secondary user should not carry out data transmission due to the strong interference from the primary user but perform energy harvesting only, which results in zero data rate for this time slot but yields potential long-term benefits. In this paper, a deep reinforcement learning (DRL) approach is applied to emulate this intuition, where the deep deterministic policy gradient (DDPG) algorithm is employed together with convex optimization. Our simulation results demonstrate that the proposed DRL assisted NOMA transmission scheme can yield significant performance gains over two benchmark schemes. [ABSTRACT FROM AUTHOR]

While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, a recent trend in AutoML is to focus on neural architecture search. In this paper, we introduce Auto-PyTorch, which brings together the best of these two worlds by jointly and robustly optimizing the network architecture and the training hyperparameters to enable fully automated deep learning (AutoDL). Auto-PyTorch achieves state-of-the-art performance on several tabular benchmarks by combining multi-fidelity optimization with portfolio construction for warmstarting and ensembling of deep neural networks (DNNs) and common baselines for tabular data. To thoroughly study our assumptions on how to design such an AutoDL system, we additionally introduce a new benchmark on learning curves for DNNs, dubbed LCBench, and run extensive ablation studies of the full Auto-PyTorch on typical AutoML benchmarks, eventually showing that Auto-PyTorch performs better than several state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

It is widely acknowledged that the success of deep learning is built upon large-scale training data and tremendous computing power. However, the data and computing power are not always available for many real-world applications. In this paper, we address the machine learning problem where it lacks training data and limits computing power. Specifically, we investigate domain adaptation which is able to transfer knowledge from one labeled source domain to an unlabeled target domain, so that we do not need much training data from the target domain. At the same time, we consider the situation that the running environment is confined, e.g., in edge computing the end device has very limited running resources. Technically, we present the Faster Domain Adaptation (FDA) protocol and further report two paradigms of FDA: early stopping and amid skipping. The former accelerates domain adaptation by multiple early exit points. The latter speeds up the adaptation by wisely skip several amid neural network blocks. Extensive experiments on standard benchmarks verify that our method is able to achieve the comparable and even better accuracy but employ much less computing resources. To the best of our knowledge, there are very few works which investigated accelerating knowledge adaptation in the community. This work is expected to inspire the topic for more discussion. [ABSTRACT FROM AUTHOR]

Depth maps acquired with ToF cameras have a limited accuracy due to the high noise level and to the multi-path interference. Deep networks can be used for refining ToF depth, but their training requires real world acquisitions with ground truth, which is complex and expensive to collect. A possible workaround is to train networks on synthetic data, but the domain shift between the real and synthetic data reduces the performances. In this paper, we propose three approaches to perform unsupervised domain adaptation of a depth denoising network from synthetic to real data. These approaches are respectively acting at the input, at the feature and at the output level of the network. The first approach uses domain translation networks to transform labeled synthetic ToF data into a representation closer to real data, that is then used to train the denoiser. The second approach tries to align the network internal features related to synthetic and real data. The third approach uses an adversarial loss, implemented with a discriminator trained to recognize the ground truth statistic, to train the denoiser on unlabeled real data. Experimental results show that the considered approaches are able to outperform other state-of-the-art techniques and achieve superior denoising performances. [ABSTRACT FROM AUTHOR]

Due to the diversity of power consumption patterns, the false positive rate (FPR) of data-driven electricity theft detection (ETD) methods is too high to meet practical needs, which severely restricts the engineering application of data-based methods. To reduce FPR of ETD methods based on advanced metering infrastructure (AMI), a deep neural network with low FPR (LFPR-DNN) is proposed in this paper. First, a deep model is constructed based on one-dimensional convolution and residual network, which can automatically extract features from consumption data. Then, a two-stage training scheme is used to train the network. In the first stage, the conventional gradient descent algorithm is used to update the network weights. To minimize the impact of data imbalance on detection performance, focal loss is used. Besides, grid search is used to optimize the hyper-parameters of the model. In the second stage, with FPR as the optimization objective, the particle swarm optimization (PSO) algorithm is used to train the network. Finally, the proposed LFPR-DNN is verified by using the open Irish data set. Compared to other state-of-the-art classifiers, LFPR-DNN has the lowest FPR with 0.29% and the highest AUC with 99.42%. The FPR is reduced by an order of magnitude, which verifies the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This paper proposes a robust method to screen patients with sleep apnea syndrome (SAS) using a single-lead electrocardiogram (ECG). This method consists of minute-by-minute abnormal breathing detection and apnea-hypopnea index (AHI) estimation. Heartbeat interval and ECG-derived respiration (EDR) are calculated using the single-lead ECG and used to train the models, including ResNet18, ResNet34, and ResNet50. The proposed method, using data from 1232 subjects, was developed with two open datasets and experimental data and evaluated using two additional open datasets and data acquired from an abdomen-attached wearable device (in total, data from 189 subjects). ResNet18 showed the best results, having an average Cohen's kappa coefficient of 0.57, in the abnormal breathing detection. Moreover, SAS patient classification, with 15 as the AHI threshold, yielded an average Cohen's kappa coefficient of 0.71. The results of patient classification were biased toward data from the wearable patch-type device, which may be influenced by different ECG waveforms. The proposed method is tuned with a sample of the data from the device, and the performance result of Cohen's kappa increased from 0.54 to 0.91 for SAS patient classification. Our method, proposed in this paper, achieved equivalent performance results with data recorded using an abdomen-attached wearable device and two open datasets used in previous studies, although the method had not used those data during model training. The proposed method could reduce the development costs of commercial software, as it was developed using open datasets, has robust performance throughout all datasets. [ABSTRACT FROM AUTHOR]

Intelligent reflecting surface (IRS), which consists of a large number of tunable reflective elements, is capable of enhancing the wireless propagation environment in a cellular network by intelligently reflecting the electromagnetic waves from the base-station (BS) toward the users. The optimal tuning of the phase shifters at the IRS is, however, a challenging problem, because due to the passive nature of reflective elements, it is difficult to directly measure the channels between the IRS, the BS, and the users. Instead of following the traditional paradigm of first estimating the channels then optimizing the system parameters, this paper advocates a machine learning approach capable of directly optimizing both the beamformers at the BS and the reflective coefficients at the IRS based on a system objective. This is achieved by using a deep neural network to parameterize the mapping from the received pilots (plus any additional information, such as the user locations) to an optimized system configuration, and by adopting a permutation invariant/equivariant graph neural network (GNN) architecture to capture the interactions among the different users in the cellular network. Simulation results show that the proposed implicit channel estimation based approach is generalizable, can be interpreted, and can efficiently learn to maximize a sum-rate or minimum-rate objective from a much fewer number of pilots than the traditional explicit channel estimation based approaches. [ABSTRACT FROM AUTHOR]

This paper investigates the stochastic optimization problem focusing on developing scalable parallel algorithms for deep learning tasks. Our solution involves a reformation of the objective function for stochastic optimization in neural network models, along with a novel parallel computing strategy, coined the weighted aggregating stochastic gradient descent (WASGD). Following a theoretical analysis on the characteristics of the new objective function, WASGD introduces a decentralized weighted aggregating scheme based on the performance of local workers. Without any center variable, the new method automatically gauges the importance of local workers and accepts them by their contributions. Furthermore, we have developed an enhanced version of the method, WASGD+, by (1) implementing a designed sample order and (2) upgrading the weight evaluation function. To validate the new method, we benchmark our pipeline against several popular algorithms including the state-of-the-art deep neural network classifier training techniques (e.g., elastic averaging SGD). Comprehensive validation studies have been conducted on four classic datasets: CIFAR-100, CIFAR-10, Fashion-MNIST, and MNIST. Subsequent results have firmly validated the superiority of the WASGD scheme in accelerating the training of deep architecture. Better still, the enhanced version, WASGD+, is shown to be a significant improvement over its prototype. [ABSTRACT FROM AUTHOR]

Hospitals can predetermine the admission rate and facilitate resource allocation based on valid emergency requests and bed capacity estimation. The excess unoccupied beds can be determined with the help of forecasting the number of discharged patients. Extracting predictive features and mining the temporal patterns from historical observations are crucial for accurate and reliable forecasts. Machine learning algorithms have demonstrated the ability to learn temporal knowledge and make predictions for unseen inputs. This paper utilizes several machine learning algorithms to forecast the inpatient discharges of Singapore hospitals and compare them with statistical methods. A novel ensemble deep learning algorithm based on random vector functional links is established to predict inpatient discharges. The ensemble deep learning framework is optimized in a greedy layer-wise fashion. Several forecasting metrics and statistical tests are utilized to demonstrate the proposed method’s superiority. The proposed algorithm statistically outperforms the benchmark with a ranking of 1.875. Finally, practical implications and future directions are discussed. [ABSTRACT FROM AUTHOR]

In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining. Since the inseparable samples are often mixed with hard samples, current informative sample mining strategies used to deal with inseparable problem may bring up some side-effects, such as instability of objective function, etc. To alleviate this problem, we propose a novel distance metric learning algorithm, named adaptive neighborhood metric learning (ANML). In ANML, we design two thresholds to adaptively identify the inseparable similar and dissimilar samples in the training procedure, thus inseparable sample removing and metric parameter learning are implemented in the same procedure. Due to the non-continuity of the proposed ANML, we develop an ingenious function, named log-exp mean function to construct a continuous formulation to surrogate it, which can be efficiently solved by the gradient descent method. Similar to Triplet loss, ANML can be used to learn both the linear and deep embeddings. By analyzing the proposed method, we find it has some interesting properties. For example, when ANML is used to learn the linear embedding, current famous metric learning algorithms such as the large margin nearest neighbor (LMNN) and neighbourhood components analysis (NCA) are the special cases of the proposed ANML by setting the parameters different values. When it is used to learn deep features, the state-of-the-art deep metric learning algorithms such as Triplet loss, Lifted structure loss, and Multi-similarity loss become the special cases of ANML. Furthermore, the log-exp mean function proposed in our method gives a new perspective to review the deep metric learning methods such as Prox-NCA and N-pairs loss. At last, promising experimental results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

With the new feature of multi-energy coupling and the advancement of the energy market, Energy Internet (EI) has higher requirements for the efficiency and applicability of integrated energy response. This paper proposes an indirect multi-energy transaction (IMET) to promote multi-energy collaborative optimization in local energy market (LEM) and improve energy utilization through personalized responses from We-Energies (WEs). Firstly, an indirect customer-to-customer multi-energy transaction is modeled for local multi-energy coupling market which can satisfy privacy, preference and autonomy of users. The efficiency of energy matching can be promoted through the participation of conversion devices. In addition, multi-time scale hybrid trading mechanism is constructed with the consideration of the transmission speed of different energy sources. Meanwhile, energy transaction process is built as a Markov decision process (MDP) with deep reinforcement learning algorithm so that the system modeling error can be successfully avoided. Furthermore, a distributed training structure is utilized to obtain more experience for a wider range of scenarios. The results of numerical simulations demonstrate the performance of the proposed method. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNNs) are currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful selection of their building blocks (e.g., residual blocks, rectifiers, sophisticated normalization schemes, to mention but a few). In this paper, we propose $\Pi$ Π -Nets, a new class of function approximators based on polynomial expansions. $\Pi$ Π -Nets are polynomial neural networks, i.e., the output is a high-order polynomial of the input. The unknown parameters, which are naturally represented by high-order tensors, are estimated through a collective tensor factorization with factors sharing. We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks. We empirically demonstrate that $\Pi$ Π -Nets are very expressive and they even produce good results without the use of non-linear activation functions in a large battery of tasks and signals, i.e., images, graphs, and audio. When used in conjunction with activation functions, $\Pi$ Π -Nets produce state-of-the-art results in three challenging tasks, i.e., image generation, face verification and 3D mesh representation learning. The source code is available at https://github.com/grigorisg9gr/polynomial_nets. [ABSTRACT FROM AUTHOR]

Coded distributed computing(CDC) has shown great potentials to solve the unexpected delay caused by stragglers in distributed computing. In this paper, we focus on the auction design for efficient resource allocation in CDC. Specifically, we aim to design a learning auction mechanism to handle heterogeneous user demands and also to free users from the complexity of specifying valuations for resource combinations, which increases exponentially with the resource dimensions. The user demand type is heterogeneous according to different variation trends of the value with finish time and workload, which is modeled by deep learning. The platform would allocate resources according to the user value function. Then users do not need to consider the complex relationship between uncertain finish time and resource configuration in CDC. Due to the inference error of the learning model and the complexity of calculating uncertain finish time, the considered social welfare optimization problem is a non-linear and non-convex integer problem. Even worse, the typical VCG-based payment scheme cannot guarantee truthfulness with the inference error. In response to these difficulties, we transform the social welfare optimization problem into a mixed integer programming problem which already has efficient solutions. The social welfare gap caused by the inference error is analyzed theoretically. The relationship between the utility regret of reporting truthfully and the inference error is also analyzed. We prove that our mechanism satisfies incentive alignment and individual rationality. Extensive experiments show the superiority of our mechanism compared with existing ones. [ABSTRACT FROM AUTHOR]

Permanent magnet localization (PML) is a nascent method of wireless motion tracking that can estimate the 5D state (3D position and 2D orientation) of a cylindrical magnet from its magnetic field. PML is well suited for applications where a wireless tracking is crucial, and in particular for tongue motion which opens up many new interesting applications. To allow its usage outside of a research lab, our tongue tracking system relies on the PML to avoid impeding tongue’s natural motion due to its wireless tracking method and ensure safe use inside the mouth. Our tracking module is embedded in a headset to be portable and simple to use while being affordable by relying on the mass-produced components. The classical implementation of PML has many shortcomings that limit its practicality for real-world applications because it is computationally intensive due to its iterative algorithm, subject to local minimum convergence issues, and sensitive to its initial state and calibration parameters. Additionally, its physical model is an approximation that is only valid in limited tracking conditions. In this paper, we investigated the potential of deep learning to create a PML model for tongue tracking by training a feedforward neural network (3 layers, 100 neurons per layer) on a dataset composed of ∼1.7 million states spanning a volume of $10\times 10\times 10$ cm3. Our PML was validated on 337 000 states in a $4\times 6\times 7$ cm3 volume and tested on 100 000 samples emulating a more natural tongue motion with curves and twists. A fully automated 5D positional stage was engineered by our team to collect these large datasets of the 5D magnet states. Our PML prediction, limited to the magnet’s 3D positions in this paper, reaches positional errors of 1.4 mm (median) and 1.8 mm (Q3). [ABSTRACT FROM AUTHOR]