4.6 Article

Robust Spike-Based Continual Meta-Learning Improved by Restricted Minimum Error Entropy Criterion

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

BiCoSS: Toward Large-Scale Cognition Brain With Multigranular Neuromorphic Architecture

Shuangming Yang et al.

Summary: The article introduces a biologically-inspired cognitive supercomputing system, BiCoSS, which integrates multiple GRs of SNNs to create a hybrid neuromorphic platform with efficient and scalable architecture and low power consumption. The system has successfully replicated various biological cognitive activities, demonstrating its high performance and potential applications.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022)

Article Computer Science, Artificial Intelligence

Weighted Error Entropy-Based Information Theoretic Learning for Robust Subspace Representation

Yuanman Li et al.

Summary: The assumption of independent and identically distributed noise in most representation learning frameworks may not hold in practical scenarios. The proposed independent and piecewise identically distributed noise model provides a better description of complex noise and leads to superior robustness in learning methods against various types of noise. The developed information-theoretic learning framework demonstrates significant performance gains in subspace clustering and image recognition compared to existing approaches.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022)

Article Computer Science, Artificial Intelligence

Restricted Minimum Error Entropy Criterion for Robust Classification

Yuanhao Li et al.

Summary: The instantiation of MEE on robust classification is lacking in the literature, thus a specific criterion called Restricted MEE (RMEE) is proposed with optimization and convergence analysis. Experimental results demonstrate the superior robustness of RMEE on synthetic and real datasets, as well as its practical impact on noisy electroencephalogram dataset.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022)

Article Computer Science, Artificial Intelligence

CerebelluMorphic: Large-Scale Neuromorphic Model and Architecture for Supervised Motor Learning

Shuangming Yang et al.

Summary: This article introduces a large-scale cerebellar network model and a cerebellum-inspired neuromorphic architecture, demonstrating improved biomimicry. Experimental results show that real-time operation can be achieved, with system throughput up to 4.70 times larger than previous works.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022)

Review Biochemical Research Methods

Neural interface systems with on-device computing: machine learning and neuromorphic architectures

Jerald Yoo et al.

Summary: The development of neural interface and brain-machine interface systems has opened up new possibilities for treating various neurological disorders through the integration of artificial intelligence and machine learning. This trend towards combining advanced technologies will lead to the creation of low-power, smart, and miniaturized therapeutic devices for a wide range of neurological and psychiatric disorders.

CURRENT OPINION IN BIOTECHNOLOGY (2021)

Article Physics, Multidisciplinary

Multiscale Entropy Analysis of Short Signals: The Robustness of Fuzzy Entropy-Based Variants Compared to Full-Length Long Signals

Airton Monte Serrat Borin Jr et al.

Summary: The study compared MSE algorithm variations adapted to short time series and found that fuzzy MSE versions have minimal errors compared to non-fuzzy algorithms for different time series lengths. Traditional multiscale entropy algorithm with fuzzy counting showed similar accuracy to alternative algorithms with better computing performance. The findings suggest selecting different fuzzy exponents based on time series length for optimal accuracy.

ENTROPY (2021)

Article Neurosciences

Efficient Spike-Driven Learning With Dendritic Event-Based Processing

Shuangming Yang et al.

Summary: The study presents a novel algorithm to solve the credit assignment problem in neuromorphic computing, with experimental results showing high performance. Learning capability is found to be influenced by the degree of dendritic segregation and the form of synaptic feedback connections. This algorithm bridges biological learning and neuromorphic learning.

FRONTIERS IN NEUROSCIENCE (2021)

Article Computer Science, Artificial Intelligence

Few-Shot Learning in Spiking Neural Networks by Multi-Timescale Optimization

Runhao Jiang et al.

Summary: This study proposed a multi-timescale optimization framework aiming to collaboratively optimize the short-term learning and long-term evolution of neural dynamics, enabling SNNs to achieve better performance in few-shot learning tasks.

NEURAL COMPUTATION (2021)

Article Automation & Control Systems

Effects of Outliers on the Maximum Correntropy Estimation: A Robustness Analysis

Badong Chen et al.

Summary: In this paper, the influence of outliers on the solution of the maximum correntropy criterion (MCC) is investigated in the context of parameter estimation for a simple linear errors-in-variables (EIVs) model. A upper bound on the estimation error is derived, showing that the MCC solution can approach the true value of the unknown parameter even with large outliers. Illustrative examples are provided to verify and clarify the theory.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2021)

Review Automation & Control Systems

Recent Progress in Transistor-Based Optoelectronic Synapses: From Neuromorphic Computing to Artificial Sensory System

Sung Woon Cho et al.

Summary: Optoelectronic synapses are promising neuromorphic devices that mimic synaptic plasticity and related functions using optical means. Compared to traditional electronic synapses, using light as input signal in photonic neuromorphic chips offers advantages such as high density, low power consumption, and low crosstalk.

ADVANCED INTELLIGENT SYSTEMS (2021)

Article Automation & Control Systems

Common Spatial Patterns Based on the Quantized Minimum Error Entropy Criterion

Badong Chen et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2020)

Article Physics, Multidisciplinary

Entropy as a Robustness Marker in Genetic Regulatory Networks

Mustapha Rachdi et al.

ENTROPY (2020)

Review Computer Science, Artificial Intelligence

Neuromemristive Circuits for Edge Computing: A Review

Olga Krestinskaya et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2020)

Article Multidisciplinary Sciences

Brain-inspired replay for continual learning with artificial neural networks

Gido M. van de Ven et al.

NATURE COMMUNICATIONS (2020)

Article Automation & Control Systems

Real-Time Neuromorphic System for Large-Scale Conductance-Based Spiking Neural Networks

Shuangming Yang et al.

IEEE TRANSACTIONS ON CYBERNETICS (2019)

Review Chemistry, Physical

Memristive crossbar arrays for brain-inspired computing

Qiangfei Xia et al.

NATURE MATERIALS (2019)

Article Computer Science, Hardware & Architecture

TrueNorth: Accelerating From Zero to 64 Million Neurons in 10 Years

Michael V. DeBole et al.

COMPUTER (2019)

Review Computer Science, Artificial Intelligence

Continual lifelong learning with neural networks: A review

German I. Parisi et al.

NEURAL NETWORKS (2019)

Article Multidisciplinary Sciences

Towards artificial general intelligence with hybrid Tianjic chip architecture

Jing Pei et al.

NATURE (2019)

Review Computer Science, Artificial Intelligence

Deep learning in spiking neural networks

Amirhossein Tavanaei et al.

NEURAL NETWORKS (2019)

Article Computer Science, Artificial Intelligence

Continual learning of context-dependent processing in neural networks

Guanxiong Zeng et al.

NATURE MACHINE INTELLIGENCE (2019)

Article Computer Science, Hardware & Architecture

Loihi: A Neuromorphic Manycore Processor with On-Chip Learning

Mike Davies et al.

IEEE MICRO (2018)

Article Computer Science, Artificial Intelligence

Insights Into the Robustness of Minimum Error Entropy Estimation

Badong Chen et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2018)

Article Neurosciences

Dynamic hidden states underlying working-memory-guided behavior

Michael J. Wolff et al.

NATURE NEUROSCIENCE (2017)

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

Article Engineering, Electrical & Electronic

The SpiNNaker Project

Steve B. Furber et al.

PROCEEDINGS OF THE IEEE (2014)

Article Biochemical Research Methods

Correction: Spike-Based Reinforcement Learning in Continuous State and Action Space: When Policy Gradient Methods Fail

Eleni Vasilaki et al.

PLoS Computational Biology (2014)

Article Engineering, Electrical & Electronic

Survival Information Potential: A New Criterion for Adaptive System Training

Badong Chen et al.

IEEE TRANSACTIONS ON SIGNAL PROCESSING (2012)