Tensor Convolutional Sparse Coding with Low-Rank activations, an application to EEG analysis
Université Paris-Saclay（巴黎萨克雷大学）；CNRS（法国国家科学研究中心）；ENS Paris-Saclay（巴黎萨克雷高等师范学校）；Centre Borelli（博雷利中心）；Université Sorbonne Paris Nord（索邦巴黎北大学）；L2TI（L2TI实验室）；eXascale Infolab；University of Fribourg（弗里堡大学）
Pierre Humbert, Laurent Oudre, Nivolas Vayatis, Julien Audiffren
Recently, there has been growing interest in the analysis of spectrograms of ElectroEncephaloGram (EEG), particularly to study the neural correlates of (un)-consciousness during General Anesthesia (GA). Indeed, it has been shown that order three tensors (channels x frequencies x times) are a natural and useful representation of these signals. However this encoding entails significant difficulties, especially for convolutional sparse coding (CSC) as existing methods do not take advantage of the particularities of tensor representation, such as rank structures, and are vulnerable to the high level of noise and perturbations that are inherent to EEG during medical acts. To address this issue, in this paper we introduce a new CSC model, named Kruskal CSC (K-CSC), that uses the Kruskal decomposition of the activation tensors to leverage the intrinsic low rank nature of these representations in order to extract relevant and interpretable encodings. Our main contribution, TC-FISTA, uses multiple tools to efficiently solve the resulting optimization problem despite the increasing complexity induced by the tensor representation. We then evaluate TC-FISTA on both synthetic dataset and real EEG recorded during GA. The results show that TC-FISTA is robust to noise and perturbations, resulting in accurate, sparse and interpretable encoding of the signals.
University of Oxford（牛津大学）；The Alan Turing Institute（阿兰·图灵研究所）
Deep Convolutional Sparse Coding (D-CSC) is a framework reminiscent of deep convolutional neural networks (DCNNs), but by omitting the learning of the dictionaries one can more transparently analyse the role of the activation function and its ability to recover activation paths through the layers. Papyan, Romano, and Elad conducted an analysis of such an architecture, demonstrated the relationship with DCNNs and proved conditions under which the D-CSC is guaranteed to recover specific activation paths. A technical innovation of their work highlights that one can view the efficacy of the ReLU n…
LTCI, Télécom ParisTech, Université Paris-Saclay（LTCI，巴黎高等电信学院，巴黎萨克雷大学）；INRIA, Université Paris Saclay（法国国家信息与自动化研究所，巴黎萨克雷大学）
Frequency-specific patterns of neural activity are traditionally interpreted as sustained rhythmic oscillations, and related to cognitive mechanisms such as attention, high level visual processing or motor control. While alpha waves (8-12 Hz) are known to closely resemble short sinusoids, and thus are revealed by Fourier analysis or wavelet transforms, there is an evolving debate that electromagnetic neural signals are composed of more complex waveforms that cannot be analyzed by linear filters and traditional signal representations. In this paper, we propose to learn dedicated representations…
Ecole Normale Supérieure de Cachan（卡尚高等师范学院）；CNRS（法国国家科学研究中心）；Université Paris-Saclay（巴黎-萨克雷大学）；Université Paris 13（巴黎第十三大学）
This paper introduces a new multivariate convolutional sparse coding based on tensor algebra with a general model enforcing both element-wise sparsity and low-rankness of the activations tensors. By using the CP decomposition, this model achieves a significantly more efficient encoding of the multivariate signal-particularly in the high order/ dimension setting-resulting in better performance. We prove that our model is closely related to the Kruskal tensor regression problem, offering interesting theoretical guarantees to our setting. Furthermore, we provide an efficient optimization algorith…
Igor Sikorsky Kyiv Polytechnic Institute（伊戈尔·西科尔斯基基辅理工学院）
Here is presented an analysis of an autoencoder with binary activations $\{0, 1\}$ and binary $\{0, 1\}$ random weights. Such set up puts this model at the intersection of different fields: neuroscience, information theory, sparse coding, and machine learning. It is shown that the sparse activation of the hidden layer arises naturally in order to preserve information between layers. Furthermore, with a large enough hidden layer, it is possible to get zero reconstruction error for any input just by varying the thresholds of neurons. The model preserves the similarity of inputs at the hidden lay…
ST-Topo GAN: A Motor EEG-to-EMG Decoding Model Matched to Wrist Movement Complexity
Zhengzhou University（郑州大学）；HumVerse (Zhengzhou) Technologies Co., Ltd.（HumVerse（郑州）科技有限公司）；Henan Provincial Key Laboratory of Brain Science and Brain-Computer Interface Technology（河南省脑科学与脑机接口技术重点实验室）；Xi’an Jiaotong University（西安交通大学）；University of Electronic Science and Technology of China（电子科技大学）；Chinese Academy of Medical Sciences（中国医学科学院）
K. N. Toosi University of Technology（K. N. 图西理工大学）；Islamic Azad University（伊斯兰阿扎德大学）；University of La Rioja（拉里奥哈大学）；Deakin University（迪肯大学）；Macquarie University（麦考瑞大学）；Harvard University（哈佛大学）；University of Leicester（莱斯特大学）；Universidad de Granada（格拉纳达大学）；University of Cambridge（剑桥大学）
Schizophrenia (SZ) is a mental disorder whereby due to the secretion of specific chemicals in the brain, the function of some brain regions is out of balance, leading to the lack of coordination between thoughts, actions, and emotions. This study provides various intelligent deep learning (DL)-based methods for automated SZ diagnosis via electroencephalography (EEG) signals. The obtained results are compared with those of conventional intelligent methods. To implement the proposed methods, the dataset of the Institute of Psychiatry and Neurology in Warsaw, Poland, has been used. First, EEG sig…
Recent advances in deep learning have had a methodological and practical impact on brain-computer interface research. Among the various deep network architectures, convolutional neural networks have been well suited for spatio-spectral-temporal electroencephalogram signal representation learning. Most of the existing CNN-based methods described in the literature extract features at a sequential level of abstraction with repetitive nonlinear operations and involve densely connected layers for classification. However, studies in neurophysiology have revealed that EEG signals carry information in…
ETH Zürich（苏黎世联邦理工学院）；University of Bologna（博洛尼亚大学）；Huawei Technologies（华为技术有限公司）
Motor-Imagery Brain--Machine Interfaces (MI-BMIs)promise direct and accessible communication between human brains and machines by analyzing brain activities recorded with Electroencephalography (EEG). Latency, reliability, and privacy constraints make it unsuitable to offload the computation to the cloud. Practical use cases demand a wearable, battery-operated device with low average power consumption for long-term use. Recently, sophisticated algorithms, in particular deep learning models, have emerged for classifying EEG signals. While reaching outstanding accuracy, these models often exceed…
Uni-NTFM: A Unified Foundation Model for EEG Signal Representation Learning
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of the Chinese Academy of Sciences（中国科学院大学）；Nanyang Technological University（南洋理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Peking University（北京大学）
Columbia University（哥伦比亚大学）；Seoul National University（首尔大学）
We present neural activation coding (NAC) as a novel approach for learning deep representations from unlabeled data for downstream applications. We argue that the deep encoder should maximize its nonlinear expressivity on the data for downstream predictors to take full advantage of its representation power. To this end, NAC maximizes the mutual information between activation patterns of the encoder and the data over a noisy communication channel. We show that learning for a noise-robust activation code increases the number of distinct linear regions of ReLU encoders, hence the maximum nonlinea…
College of Computer, Nanjing University of Posts and Telecommunications（南京邮电大学计算机学院）；High Technology Research Key Laboratory of Wireless Sensor Network of Jiangsu Province（江苏省无线传感器网络高技术研究重点实验室）；Malmö University（马尔默大学）；School of Computer and Information, Anqing Normal University（安庆师范大学计算机与信息学院）
With the rapid development of Machine Learning technology applied in electroencephalography (EEG) signals, Brain-Computer Interface (BCI) has emerged as a novel and convenient human-computer interaction for smart home, intelligent medical and other Internet of Things (IoT) scenarios. However, security issues such as sensitive information disclosure and unauthorized operations have not received sufficient concerns. There are still some defects with the existing solutions to encrypted EEG data such as low accuracy, high time complexity or slow processing speed. For this reason, a classification …
School of Integrated Technology, Yonsei University（延世大学融合技术学院）
Emotion recognition based on electroencephalography (EEG) has received attention as a way to implement human-centric services. However, there is still much room for improvement, particularly in terms of the recognition accuracy. In this paper, we propose a novel deep learning approach using convolutional neural networks (CNNs) for EEG-based emotion recognition. In particular, we employ brain connectivity features that have not been used with deep learning models in previous studies, which can account for synchronous activations of different brain regions. In addition, we develop a method to ef…
Sabanci University（萨班哲大学）；Hacettepe University（哈塞特佩大学）；University of Rochester（罗切斯特大学）
Resting-state brain networks represent the intrinsic state of the brain during the majority of cognitive and sensorimotor tasks. However, no study has yet presented concise predictors of task-induced vigilance variability from spectrospatial features of the pre-task, resting-state electroencephalograms (EEG). We asked ten healthy volunteers (6 females, 4 males) to participate in 105-minute fixed-sequence-varying-duration sessions of sustained attention to response task (SART). A novel and adaptive vigilance scoring scheme was designed based on the performance and response time in consecutive t…
The high temporal resolution and the asymmetric spatial activations are essential attributes of electroencephalogram (EEG) underlying emotional processes in the brain. To learn the temporal dynamics and spatial asymmetry of EEG towards accurate and generalized emotion recognition, we propose TSception, a multi-scale convolutional neural network that can classify emotions from EEG. TSception consists of dynamic temporal, asymmetric spatial, and high-level fusion layers, which learn discriminative representations in the time and channel dimensions simultaneously. The dynamic temporal layer consi…
Driver drowsiness is one of main factors leading to road fatalities and hazards in the transportation industry. Electroencephalography (EEG) has been considered as one of the best physiological signals to detect drivers drowsy states, since it directly measures neurophysiological activities in the brain. However, designing a calibration-free system for driver drowsiness detection with EEG is still a challenging task, as EEG suffers from serious mental and physical drifts across different subjects. In this paper, we propose a compact and interpretable Convolutional Neural Network (CNN) to disco…
Drexel University（德雷塞尔大学）；University of Delaware（特拉华大学）
Artificial neural networks (ANNs), specifically deep learning networks, have often been labeled as black boxes due to the fact that the internal representation of the data is not easily interpretable. In our work, we illustrate that an ANN, trained using sparse coding under specific sparsity constraints, yields a more interpretable model than the standard deep learning model. The dictionary learned by sparse coding can be more easily understood and the activations of these elements creates a selective feature output. We compare and contrast our sparse coding model with an equivalent feed forwa…
Our ability to track multiple objects in a dynamic environment enables us to perform everyday tasks such as driving, playing team sports, and walking in a crowded mall. Despite more than three decades of literature on multiple object tracking (MOT) tasks, the underlying and intertwined neural mechanisms remain poorly understood. Here we looked at the electroencephalography (EEG) neural correlates and their changes across the three phases of a 3D-MOT task, namely identification, tracking and recall. We recorded the EEG activity of 24 participants while they were performing a 3D-MOT task with ei…
Magnetoencephalography and electroencephalography (M/EEG) are non-invasive modalities that measure the weak electromagnetic fields generated by neural activity. Estimating the location and magnitude of the current sources that generated these electromagnetic fields is a challenging ill-posed regression problem known as \emph{source imaging}. When considering a group study, a common approach consists in carrying out the regression tasks independently for each subject. An alternative is to jointly localize sources for all subjects taken together, while enforcing some similarity between them. By …
CRIA: A Cross-View Interaction and Instance-Adapted Pre-training Framework for Generalizable EEG Representations
Guangdong Provincial Key Laboratory of AI Large Model and Intelligent Cognition（人工智能大模型与智能认知广东省重点实验室）；School of Computer Science and Engineering（计算机科学与工程学院）；South China University of Technology（华南理工大学）；Pazhou Lab（琶洲实验室）；Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human（教育部健康智能感知与平行数字人工程研究中心）
FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-low Power Microcontroller
Integrated Systems Laboratory, ETH Zürich（苏黎世联邦理工学院集成系统实验室）；DEI, University of Bologna（博洛尼亚大学电气、电子与信息工程系）
Dynamic Time Wrapping (DTW) is a widely used algorithm for measuring similarities between two time series. It is especially valuable in a wide variety of applications, such as clustering, anomaly detection, classification, or video segmentation, where the time-series have different timescales, are irregularly sampled, or are shifted. However, it is not prone to be considered as a loss function in an end-to-end learning framework because of its non-differentiability and its quadratic temporal complexity. While differentiable variants of DTW have been introduced by the community, they still pres…
Advanced Research Lab, NavInfo Europe（NavInfo Europe 高级研究实验室）；Department of Mathematics and Computer Science, Eindhoven University of Technology（埃因霍温理工大学数学与计算机科学系）
Efficient continual learning in humans is enabled by a rich set of neurophysiological mechanisms and interactions between multiple memory systems. The brain efficiently encodes information in non-overlapping sparse codes, which facilitates the learning of new associations faster with controlled interference with previous associations. To mimic sparse coding in DNNs, we enforce activation sparsity along with a dropout mechanism which encourages the model to activate similar units for semantically similar inputs and have less overlap with activation patterns of semantically dissimilar inputs. Th…
Several recent results in machine learning have established formal connections between autoencoders---artificial neural network models that attempt to reproduce their inputs---and other coding models like sparse coding and K-means. This paper explores in depth an autoencoder model that is constructed using rectified linear activations on its hidden units. Our analysis builds on recent results to further unify the world of sparse linear coding models. We provide an intuitive interpretation of the behavior of these coding models and demonstrate this intuition using small, artificial datasets wit…
We address the problem of reconstructing sparse signals from noisy and compressive measurements using a feed-forward deep neural network (DNN) with an architecture motivated by the iterative shrinkage-thresholding algorithm (ISTA). We maintain the weights and biases of the network links as prescribed by ISTA and model the nonlinear activation function using a linear expansion of thresholds (LET), which has been very successful in image denoising and deconvolution. The optimal set of coefficients of the parametrized activation is learned over a training dataset containing measurement-sparse sig…
Mila - Quebec Artificial Intelligence Institute（米拉——魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）
Dynamic adaptation in single-neuron response plays a fundamental role in neural coding in biological neural networks. Yet, most neural activation functions used in artificial networks are fixed and mostly considered as an inconsequential architecture choice. In this paper, we investigate nonlinear activation function adaptation over the large time scale of learning, and outline its impact on sequential processing in recurrent neural networks. We introduce a novel parametric family of nonlinear activation functions, inspired by input-frequency response curves of biological neurons, which allows…
Harbin Engineering University（哈尔滨工程大学）；University of California, Los Angeles（加州大学洛杉矶分校）
We introduce an explainable generative model by applying sparse operation on the feature maps of the generator network. Meaningful hierarchical representations are obtained using the proposed generative model with sparse activations. The convolutional kernels from the bottom layer to the top layer of the generator network can learn primitives such as edges and colors, object parts, and whole objects layer by layer. From the perspective of the generator network, we propose a method for inducing both sparse coding and the AND-OR grammar for images. Experiments show that our method is capable of …
Qualcomm AI Research（高通人工智能研究院）；Qualcomm Technologies, Inc.（高通技术公司）
Neural-based image and video codecs are significantly more power-efficient when weights and activations are quantized to low-precision integers. While there are general-purpose techniques for reducing quantization effects, large losses can occur when specific entropy coding properties are not considered. This work analyzes how entropy coding is affected by parameter quantizations, and provides a method to minimize losses. It is shown that, by using a certain type of coding parameters to be learned, uniform quantization becomes practically optimal, also simplifying the minimization of code memo…
The deep learning revolution brought us an extensive array of neural network architectures that achieve state-of-the-art performance in a wide variety of Computer Vision tasks including among others, classification, detection and segmentation. In parallel, we have also been observing an unprecedented demand in computational and memory requirements, rendering the efficient use of neural networks in low-powered devices virtually unattainable. Towards this end, we propose a three-stage compression and acceleration pipeline that sparsifies, quantizes and entropy encodes activation maps of Convolut…
Recently, it has been observed that when representations are learnt in a way that encourages sparsity, improved performance is obtained on classification tasks. These methods involve combinations of activation functions, sampling steps and different kinds of penalties. To investigate the effectiveness of sparsity by itself, we propose the k-sparse autoencoder, which is an autoencoder with linear activation function, where in hidden layers only the k highest activities are kept. When applied to the MNIST and NORB datasets, we find that this method achieves better classification results than den…
Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks
Department of Mathematics, Ludwig-Maximilians-Universität München（慕尼黑莱布尼茨-马克斯大学数学系）；Department of Mathematics, City University of Hong Kong（香港城市大学数学系）；Department of Mathematics, The University of Sydney（悉尼大学数学系）
Indian Institute of Information Technology, Sri City（印度信息技术学院，斯里城）；Aalborg University（奥尔堡大学）；Pioneer Centre for AI（人工智能先锋中心）
Deep representation learning has gained significant momentum in advancing text-dependent speaker verification (TD-SV) systems. When designing deep neural networks (DNN) for extracting bottleneck features, key considerations include training targets, activation functions, and loss functions. In this paper, we systematically study the impact of these choices on the performance of TD-SV. For training targets, we consider speaker identity, time-contrastive learning (TCL) and auto-regressive prediction coding with the first being supervised and the last two being self-supervised. Furthermore, we st…
In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a relatively low-complexity device such as a mobile phone or edge device, and the remainder of the DNN is processed where more computing resources are available, such as in the cloud. This paper presents a novel lightweight compression technique designed specifically to code the activations of a split DNN layer, while having a low complexity suitable for edge devices and not requiring any retraining. We also present a modified entropy-constrained quantizer design algorithm optimized for clipped activ…
