检索结果-内蒙古大学图书馆

BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zheng, Kaizhong Yu, Shujian Li, Baojuan Jenssen, Robert Chen, Badong National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China The Department of Computer Science Vrije Universiteit Amsterdam Amsterdam and the Machine Learning Group UiT - Arctic University of Norway Tromsø Norway The Machine Learning Group UiT - Arctic University of Norway Tromsø Norway The School of Biomedical Engineering Fourth Military Medical University Xi’an China

Developing a new diagnostic models based on the underlying biological mechanisms rather than subjective symptoms for psychiatric disorders is an emerging consensus. Recently, machine learning-based classifiers using functional connectivity (FC) for psychiatric disorders and healthy controls are developed to identify brain markers. However, existing machine learning-based diagnostic models are prone to over-fitting (due to insufficient training samples) and perform poorly in new test environment. Furthermore, it is difficult to obtain explainable and reliable brain biomarkers elucidating the underlying diagnostic decisions. These issues hinder their possible clinical applications. In this work, we propose BrainIB, a new graph neural network (GNN) framework to analyze functional magnetic resonance images (fMRI), by leveraging the famed Information Bottleneck (IB) principle. BrainIB is able to identify the most informative edges in the brain (i.e., subgraph) and generalizes well to unseen data. We evaluate the performance of BrainIB against 3 baselines and 7 state-of-the-art brain network classification methods on three psychiatric datasets and observe that our BrainIB always achieves the highest diagnosis accuracy. It also discovers the subgraph biomarkers which are consistent to clinical and neuroimaging findings. The source code and implementation details of BrainIB are freely available at GitHub repository (https://***/SJYuCNEL/brain-and-Information-Bottleneck/). Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

Bistable Dynamics of the Brain Extracellular Matrix in the Presence of Periodically Varying Neuronal Activity 5

学校读者我要写书评

暂无评论

Bistable Dynamics of the Brain Extracellular Matrix in the P...

5th Scientific School on Dynamics of Complex Networks and their Applications, DCNA 2021

作者： Rozhnova, Maiya A. Kazantsev, Victor B. Pankratova, Evgeniya V. Department of Applied Mathematics Institute of Information Technologies Mathematics and Mechanics Lobachevsky State University of Nizhni Novgorod Nizhny Novgorod Russia Neurotechnology Department Lobachevsky State University Nizhny Novgorod Russia Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Neuroscience Research Institute Samara State Medical University Samara Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665442824

In this work, the role of the amplitude and frequency of the periodically varying neuronal firing rate in emergence of complicated dynamical modes in recently proposed mathematical model describing the change of extracellular matrix molecules concentration, was examined. Impact of the revealed co-existence of regular and chaotic modes in the extracellular matrix activity on the whole neuronal network functioning is discussed. © 2021 IEEE

关键词： Brain

CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Kaizhong Yu, Shujian Chen, Badong National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an China Department of Computer Science Vrije Universiteit Amsterdam Amsterdam Netherlands Machine Learning Group UiT - Arctic University of Norway Tromsø Norway

There is a recent trend to leverage the power of graph neural networks (GNNs) for brain-network based psychiatric diagnosis, which, in turn, also motivates an urgent need for psychiatrists to fully understand the decision behavior of the used GNNs. However, most of the existing GNN explainers are either post-hoc in which another interpretive model needs to be created to explain a well-trained GNN, or do not consider the causal relationship between the extracted explanation and the decision, such that the explanation itself contains spurious correlations and suffers from weak faithfulness. In this work, we propose a granger causality-inspired graph neural network (CI-GNN), a built-in interpretable model that is able to identify the most influential subgraph (i.e., functional connectivity within brain regions) that is causally related to the decision (e.g., major depressive disorder patients or healthy controls), without the training of an auxillary interpretive network. CI-GNN learns disentangled subgraph-level representations α and β that encode, respectively, the causal and non-causal aspects of original graph under a graph variational autoencoder framework, regularized by a conditional mutual information (CMI) constraint. We theoretically justify the validity of the CMI regulation in capturing the causal relationship. We also empirically evaluate the performance of CI-GNN against three baseline GNNs and four state-of-the-art GNN explainers on synthetic data and three large-scale brain disease datasets. We observe that CI-GNN achieves the best performance in a wide range of metrics and provides more reliable and concise explanations which have clinical evidence. The source code and implementation details of CI-GNN are freely available at GitHub repository (https://***/ZKZ-Brain/CI-GNN/). Copyright © 2023, The Authors. All rights reserved.

关键词： Diagnosis

Deep Convolutional Neural Networks with Zero-Padding: Feature Extraction and learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Han, Zhi Liu, Baichen Lin, Shao-Bo Zhou, Ding-Xuan State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Center of Intelligent Decision-Making and Machine Learning School of Management Xi’an Jiaotong University Xi’an China School of Mathematics and Statistics University of Sydney SydneyNSW2006 Australia

This paper studies the performance of deep convolutional neural networks (DCNNs) with zero-padding in feature extraction and learning. After verifying the roles of zero-padding in enabling translation-equivalence, and pooling in its translation-invariance driven nature, we show that with similar number of free parameters, any deep fully connected networks (DFCNs) can be represented by DCNNs with zero-padding. This demonstrates that DCNNs with zero-padding is essentially better than DFCNs in feature extraction. Consequently, we derive universal consistency of DCNNs with zero-padding and show its translation-invariance in the learning process. All our theoretical results are verified by numerical experiments including both toy simulations and real-data running. © 2023, CC0.

关键词： Feature extraction

Bursting activity interplay in modular neural networks in vitro 3

学校读者我要写书评

暂无评论

Bursting activity interplay in modular neural networks in vi...

3rd International Conference "Neurotechnologies and Neurointerfaces", CNN 2021

作者： Gladkov, Arseniy Pigareva, Yana Kolpakov, Vladimir Mukhina, Irina Bukatin, Anton Kazantsev, Victor Pimashkin, Alexey Cell Technology Department Central Research Laboratory Privolzhsky Research Medical University Nizhny Novgorod Russia Neurotechnology Department Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Laboratory of Renewable Energy Sources Alferov Saint-Petersburg National Research Academic University of the Russian Academy of Sciences Saint-Petersburg Russia Laboratory of Bio and Chemosensor Microsystems Institute for Analytical Instrumentation of the RAS Saint-Petersburg Russia Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia NeurotechnologyDepartment Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia

ISBN: (纸本)9781665424745

Neural networks modularity is a major challenge to study spiking pattern propagation and information processing in the brain. Sparse and heterogeneous connectivity between network modules defines spiking activity generation and interplay. Detailed study of modular network complex connectivity and dynamics is complicated by inducing retrograde or closed-loop activity. In this study, we analyzed the spiking activity of spontaneous and stimulus-induced interplay between two cultured neuronal networks (source-target) coupled with unidirectional synaptic connections, which were formed by microfluidic microchannels. Inhibition of excitatory synaptic activity in a source module abolished retrograde and closed-loop activity in the interplay. We found characteristics of electrical stimulation applied to the intermodular connections, which evoked a network-wide response in a target module. The developed approach can be applied to study synaptic plasticity in modular networks in vitro and improvement of new methods of neurointerface design. © 2021 IEEE.

关键词： Microfluidic chips

A multi-objective deep reinforcement learning algorithm for spatio-temporal latency optimization in mobile IoT-enabled edge computing networks

学校读者我要写书评

暂无评论

Simulation Modelling Practice and Theory 2025年 143卷

作者： Parisa Khoshvaght Amir Haider Amir Masoud Rahmani Farhad Soleimanian Gharehchopogh Ferzat Anka Jan Lansky Mehdi Hosseinzadeh Institute of Research and Development Duy Tan University Da Nang Vietnam School of Engineering & Technology Duy Tan University Da Nang Vietnam Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura 140401 Punjab India Department of AI and Robotics Sejong University Seoul 05006 Republic of Korea Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Engineering Ur. C. Islamic Azad University Urmia Iran Data Science Application and Research Center (VEBIM) Fatih Sultan Mehmet Vakif University Istanbul Türkiye Department of Computer Science and Mathematics Faculty of Economic Studies University of Finance and Administration Prague Czech Republic Pattern Recognition and Machine Learning Laboratory School of Computing Gachon University Seongnam Republic of Korea

The rapid increase in Mobile Internet of Things (IoT) devices requires novel computational frameworks. These frameworks must meet strict latency and energy efficiency requirements in Edge and Mobile Edge Computing (MEC) systems. Spatio-temporal dynamics, which include the position of edge servers and the timing of task schedules, pose a complex optimization problem. These challenges are further exacerbated by the heterogeneity of IoT workloads and the constraints imposed by device mobility. The balance between computational overhead and communication challenges is also a problem. To solve these issues, advanced methods are needed for resource management and dynamic task scheduling in mobile IoT and edge computing environments. In this paper, we propose a Deep Reinforcement learning (DRL) multi-objective algorithm, called a Double Deep Q-learning (DDQN) framework enhanced with Spatio-temporal mobility prediction, latency-aware task offloading, and energy-constrained IoT device trajectory optimization for federated edge computing networks. DDQN was chosen for its optimize stability and reduced overestimation in Q-values. The framework employs a reward-driven optimization model that dynamically prioritizes latency-sensitive tasks, minimizes task migration overhead, and balances energy efficiency across devices and edge servers. It integrates dynamic resource allocation algorithms to address random task arrival patterns and real-time computational demands. Simulations demonstrate up to a 35 % reduction in end-to-end latency, a 28 % improvement in energy efficiency, and a 20 % decrease in the deadline-miss ratio compared to benchmark algorithms.

关键词：

Model of ‘implant-host’ neural circuits in a microfluidic chip in vitro 8

学校读者我要写书评

暂无评论

Model of ‘implant-host’ neural circuits in a microfluidic ...

8th International School and Conference "Saint Petersburg OPEN 2021" on Optoelectronics, Photonics, Engineering and Nanostructures, SPbOPEN 2021

作者： Kolpakov, V.N. Pigareva, Y.I. Gladkov, A.A. Bukatin, A.S. Kazantsev, V.B. Mukhina, I.V. Pimashkin, A.S. Neurotechnology Department Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod603950 Russia Cell Technology Department Central Research Laboratory Privolzhsky Research Medical University Nizhny Novgorod603005 Russia Laboratory of Renewable Energy Sources Alferov Saint-Petersburg National Research Academic University of the Russian Academy of Sciences Saint-Petersburg194021 Russia Laboratory of Bio and Chemosensor Microsystems Institute for Analytical Instrumentation of the RAS Saint-Petersburg198095 Russia Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University 1 Universitetskaya Str. Innopolis420500 Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University 14 Nevsky Str. Kaliningrad236016 Russia

In this study, we developed a new model of neuronal cells plating into a developed neural network to study functional integration using microfluidic methods. The integration was modeled in a three-chamber microfluidic chip by growing two weakly coupled neuronal networks and enhancing its connectivity by plating new dissociated cells. The direction of connections was formed by the asymmetric design of the chip. Such technology can be used to develop a new type of scaffold to recover the modular structure of the network. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Microfluidics

A Structured Prediction Approach for Robot Imitation learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Duan, Anqing Batzianoulis, Iason Camoriano, Raffaello Rosasco, Lorenzo Pucci, Daniele Billard, Aude Robotics and Machine Intelligence Laboratory The Hong Kong Polytechnic University Hong Kong Learning Algorithms and Systems Laboratory École Polytechnique Fédérale de Lausanne Lausanne Switzerland Visual And Multimodal Applied Learning Laboratory Politecnico di Torino Turin Italy DIBRIS Università degli Studi di Genova Genoa Italy Laboratory for Computational and Statistical Learning IIT@MIT Istituto Italiano di Tecnologia Massachusetts Institute of Technology CambridgeMA United States Center Università di Genova Genoa Italy Dynamic Interaction Control research line Italian Institute of Technology Genoa Italy

We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form of supervised learning that enables learning models to operate on output spaces with complex structures. Through the lens of structured prediction, we show how robots can learn to imitate trajectories belonging to not only Euclidean spaces but also Riemannian manifolds. Exploiting ideas from information theory, we propose a class of loss functions based on the f-divergence to measure the information loss between the demonstrated and reproduced probabilistic trajectories. Different types of f-divergence will result in different policies, which we call imitation modes. Furthermore, our approach enables the incorporation of spatial and temporal trajectory modulation, which is necessary for robots to be adaptive to the change in working conditions. We benchmark our algorithm against state-of-the-art methods in terms of trajectory reproduction and adaptation. The quantitative evaluation shows that our approach outperforms other algorithms regarding both accuracy and efficiency. We also report real-world experimental results on learning manifold trajectories in a polishing task with a KUKA LWR robot arm, illustrating the effectiveness of our algorithmic framework. Copyright © 2023, The Authors. All rights reserved.

关键词： Trajectories

Relevance attack on detectors

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Sizhe He, Fan Huang, Xiaolin Zhang, Kun Department of Automation The Institute of Medical Robotics The MOE Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China Philosophy Department and Machine Learning Department Carnegie Mellon University 5000 Forbes Ave PittsburghPA15213 United States

This paper focuses on high-transferable adversarial attacks on detectors, which are hard to attack in a black-box manner, because of their multiple-output characteristics and the diversity across architectures. To pursue a high attack transferability, one plausible way is to find a common property across detectors, which facilitates the discovery of common weaknesses. We are the first to suggest that the relevance map from interpreters for detectors is such a property. Based on it, we design a Relevance Attack on Detectors (RAD), which achieves a state-of-the-art transferability, exceeding existing results by above 20%. On MS COCO, the detection mAPs for all 8 black-box architectures are more than halved and the segmentation mAPs are also significantly influenced. Given the great transferability of RAD, we generate the first adversarial dataset for object detection and instance segmentation, i.e., Adversarial Objects in COntext (AOCO), which helps to quickly evaluate and improve the robustness of detectors. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection