检索结果-内蒙古大学图书馆

Neuronal Mechanisms and Transformations Encoding Time-Varying Signals

NEURON 2016年第4期91卷 718-721页

作者： Petkov, Christopher I. Bendor, Daniel Newcastle Univ Sch Med Inst Neurosci Framlington Pl Newcastle Upon Tyne NE2 4HH Tyne & Wear England UCL Dept Expt Psychol 26 Bedford Way London WC1H 0AP England

Sensation in natural environments requires the analysis of time-varying signals. While previous work has uncovered how a signal's temporal rate is represented by neurons in sensory cortex, in this issue of Neuron,... 详细信息

关键词： primate intracellular neuron mechanism rate coding auditory

来源：评论

学校读者我要写书评

暂无评论

Learning in Feedback-driven Recurrent Spiking Neural Networks using full-FORCE Training

Learning in Feedback-driven Recurrent Spiking Neural Network...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Paul, Ankita Wagner, Stefan Das, Anup Drexel Univ Philadelphia PA USA

ISBN: (数字)9781728186719

ISBN: (纸本)9781728186719

Feedback-driven recurrent spiking neural networks (RSNNs) are powerful computational models that can mimic dynamic systems. However, the presence of a feedback loop from the readout to the recurrent layer de-stabilizes the learning mechanism and prevents it from converging. Here, we propose a supervised training procedure for RSNNs, where a second network is introduced only during the training, to provide hint for the target dynamics. The proposed training procedure consists of generating targets for both recurrent and readout layers (i.e., for a full RSNN system). It uses the recursive least square-based First-Order and Reduced Control Error (FORCE) algorithm to fit the activity of each layer to its target. The proposed full-FORCE training procedure reduces the amount of modifications needed to keep the error between the output and target close to zero. These modifications control the feedback loop, which causes the training to converge. We demonstrate the improved performance and noise robustness of the proposed full-FORCE training procedure to model 8 dynamical systems using RSNNs with leaky integrate and fire (LIF) neurons and rate coding. For energy-efficient hardware implementation, an alternative time-to-first-spike (TTFS) coding is implemented for the full-FORCE training procedure. Compared to rate coding, full-FORCE with TTFS coding generates fewer spikes and facilitates faster convergence to the target dynamics.

关键词： spiking neural networks (SNNs) recurrent SNNs (RSNNs) liquid state machine (LSM) neuromorphic computing rate coding time-to-first spike (TTFS) coding dynamical system

来源：评论

学校读者我要写书评

暂无评论

An experimental and model based investigation of the potential and limitations of surface EMG spectral analysis for assessment of motor unit recruitment strategy

An experimental and model based investigation of the potenti...

引用

23rd Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society

作者： Farina, D Merletti, R Politecn Torino Ctr Bioingn Dept Elect Turin Italy

ISBN: (纸本)0780372115

Characteristic frequencies of surface EMG power spectrum have been used in the past as indicative of motor unit (MU) recruitment, since they are rather insensitive to changes of MU firing rates and thus they should remain constant when only rate coding is used to modulate muscle force. However, this speculation h as not been yet validated by simulated and experimental data. In this paper, a model of surface EMG signal generation and detection is used to simulate EMG signals detected during linearly increasing force contractions. Different MU control strategies (corresponding to different ways for force generation by recruitment and rate coding) are simulated. A number of simulations are performed to study the affect of random distribution of MUs in the muscle's cross-section upon the surface EMG. The results are compared with those obtained analyzing the EMG signals detected experimentally during linearly increasing force contractions of the biceps brachii muscle in 10 subjects. Results show that the volume conductor properties may act as confounding factors which may mask any relationship between characteristic spectral frequencies and conduction velocity as a size principle parameter. It is concluded that more advanced signal processing techniques which aim at the analysis of single MU activity are required for the surface EMG based assessment of central nervous system control strategy.

关键词： rate coding surface electromyography motor unit recruitment EMG spectral analysis muscle fiber conduction velocity

来源：评论

学校读者我要写书评

暂无评论

Neural coding: adapting spike generation for embedded hardware classification

Neural coding: adapting spike generation for embedded hardwa...

引用

International Joint Conference on Neural Networks (IJCNN) held as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

作者： Abderrahmane, Nassim Miramond, Benoit Univ Cote dAzur LEAT CNRS Nice France

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169262

Recent literature considers that Spiking Neural Networks are now a serious alternative to Formal Neural Networks for embedded artificial intelligence. The changes in the information coding and the elementary neural computation make them more efficient than FNNs in terms of power consumption and chip surface occupation. However, these results are often based on simple neural network topologies with basic data-sets. In this paper, we study the behavior of Spiking Convolutional Neural Networks when applied to two different classification tasks. To do so, we analyze the spiking activity on both MNIST and GTSRB data-sets using different rate-based and temporal coding schemes. Notably, the Spike Select method is confronted to First Spike and Jittered Periodic methods in terms of prediction accuracy and spiking activity. Finally, we conclude about spike generation within spiking CNNs for embedded hardware classification.

关键词： Spike Generation Temporal coding rate coding Spiking Neural Networks Convolutional Neural Networks Embedded Systems Neuromorphic Computing

来源：评论

学校读者我要写书评

暂无评论

Adaptive-Critic-Based Control of a Synchronous Generator in a Power System Using Biologically Inspired Artificial Neural Networks

Adaptive-Critic-Based Control of a Synchronous Generator in ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Dai, Jing Venayagamoorthy, Ganesh K. Harley, Ronald G. Deng, Yi Potter, Steve M. Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA Clemson Univ Holcombe Dept Elect & Comp Engn Real Time Power & Intelligent Syst Lab Clemson SC 29634 USA Georgia Inst Technol Coulter Dept Biomed Engn Atlanta GA 30332 USA Emory Univ Sch Med Atlanta GA 30332 USA Georgia Inst Technol Lab Neuroengn Atlanta GA 30332 USA

ISBN: (纸本)9781479919598

This paper proposes an adaptive critic design(A CD) based control method of a generator in a single machine infinite bus (SMm) power system, by using a biologically-inspired artificial neural network (BIANN). A heuristic dynamic programming (HDP) based optimal controller applying three BIANNs is designed for the control of the turbo generator in the SMm system. By developing a numerical derivative calculation algorithm, the difficulties in back-propagating errors through a BIANN are overcome. The HDP-BIANN controller for the turbo generator in the SMm system is trained and run online for different operating conditions. The results show that the HDP-BIANN controller improves the system damping as well as dynamic transient stability more effectively than the conventional controllers (CONVC) for not only small step changes, but also large disturbances such as a three phase short circuit. This is the first time that a BIANN is used for closed-loop optimal control of a power system.

关键词： Adaptive critic design (ACD) biologically inspired artificial neural network (BIANN) neurocontrol power system rate coding spiking neural network

来源：评论

学校读者我要写书评

暂无评论

Reservoir-computing-based, Biologically-inspired Artificial Neural Network for Modeling of a Single Machine Infinite Bus Power System

Reservoir-computing-based, Biologically-inspired Artificial ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Dai, Jing Venayagamoorthy, Ganesh Kumar Harley, Ronald G. Potter, Steve M. Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA Clemson Univ Dept Elect & Comp Engn Clemson SC 29634 USA Georgia Inst Technol Dept Biomed Engn Atlanta GA 30332 USA Emory Univ Sch Med Atlanta GA 30322 USA Georgia Inst Technol Lab Neuroengn Atlanta GA 30332 USA

ISBN: (纸本)9781467314909

Inspired by living neuron networks (LNNs) in the brain, artificial neural networks (ANNs) have been broadly used in various applications as a computational intelligence tool. However, due to many fundamental differences between ANNs and LNNs, despite the mature training mechanisms for ANNs, it is often challenging to use LNNs as a computational intelligence tool. To bridge the gap between ANNs and LNNs, a novel type of artificial neural network, i.e. biologically-inspired artificial neural network (BIANN) is proposed in this paper. The BIANN, which is based on spiking neuron models of LNNs, processes information in a more "brain-like" fashion than conventional ANNs. A reservoir-computing-based training approach is also proposed for BIANNs to serve as a novel modeling and control tool for practical applications. The feasibility of the proposed BIANN is illustrated for the prediction of a synchronous generator's speed and terminal voltage signals in a single machine infinite bus electric power system setup. The proposed BIANN model is able to provide an accurate prediction for online monitoring of a generator.

关键词： spiking neural network rate coding biologically-inspired artificial neural network reservoir computing power system

来源：评论

学校读者我要写书评

暂无评论

Repeat Burst for Timing Code in Excitatory Neuronal Network on Multi-Electrode Array

Repeat Burst for Timing Code in Excitatory Neuronal Network ...

引用

2010 3rd International Conference on Biomedical Engineering and Informatics (BMEI 2010)

作者： Li, Xiangning Pu, Jiangbo Chen, Wenjuan Zhou, Wei Gong, Hui Luo, Qingming Huazhong Univ Sci & Technol Britton Chance Ctr Biomed Photon Wuhan Natl Lab Optoelect Wuhan 430074 Hubei Peoples R China

ISBN: (纸本)9781424464968

Concise coding for input plays an important role in neural signal processing. In previous studies, three types of neural signal coding were raised: rate, timing and population coding. By multi-electrode array, the coding of input intensities in cultured hippocampal neuronal networks was examined. In excitatory neuronal network, responses to input intensities focused on the three periods: 1 similar to 10 ms, 11 similar to 30 ms, 41 similar to 60 ms. The dynamics on firing rate to input intensities in each timings was distinct: in 1 similar to 10 ms, the sublinear relationship to increasing input intensities was exhibited over the whole input range;in 11 similar to 30 ms, only a transition was occurred in inputs from 300 to 400mV;in 41 similar to 60 ms, a linear increase with input from 300 to 600 mV. These results suggest that the coding to input intensities was a complex mode that is repeat burst based-on timing in high density cultured neuronal network.

关键词： input intensity excitatory neuronal network multi-electrode array timing coding rate coding

来源：评论

学校读者我要写书评

暂无评论

Evaluating Encoding and Decoding Approaches for Spiking Neuromorphic Systems 22

Evaluating Encoding and Decoding Approaches for Spiking Neur...

引用

International Conference on Neuromorphic Systems (ICONS)

作者： Schuman, Catherine D. Rizzo, Charles McDonald-Carmack, John Skuda, Nicholas Plank, James S. Univ Tennessee Dept EECS Knoxville TN 37996 USA

ISBN: (纸本)9781450397896

A challenge associated with effectively using spiking neuromorphic systems is how to communicate data to and from the neuromorphic implementation. Unless a neuromorphic or event-based sensing system is used, data has to be converted into spikes to be processed as input by the neuromorphic system. The output spikes produced by the neuromorphic system have to be turned back into a value or decision. There are a variety of commonly used input encoding approaches, such as rate coding, temporal coding, and population coding, as well as several commonly used output approaches, such as voting or first-to-spike. However, it is not clear which is the most appropriate approach to use or whether the choice of encoding or decoding approach has a significant impact on performance. In this work, we evaluate the performance of several encoding and decoding approaches on classification, regression, and control tasks. We show that the choice of encoding and decoding approaches significantly impact performance on these tasks, and we make recommendations on how to select the appropriate encoding and decoding approaches for real-world applications.

关键词： spiking neural networks neuromorphic computing encoding decoding rate coding temporal coding voting

来源：评论

学校读者我要写书评

暂无评论

ASIC Implementation of Efficient 512-Neuron 256K-Synapses Digital Neuromorphic Processor with On-Chip Encoding in 22nmFDX

ASIC Implementation of Efficient 512-Neuron 256K-Synapses Di...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Ghonem, Ahmed Zaky Tawfik, Eslam Yahya Ohio State Univ Columbus OH 43210 USA

ISBN: (纸本)9798350330991;9798350331004

There is a rising demand for AI workloads running on the edge that are increasingly complex, calling for more efficient computing platforms. Neuromorphic hardware is a class of electronic circuits and devices that aim to mimic a biological brain's functionality and computational efficiency. In this work, we propose a 512 neuron 256K synapses LIF-based digital neuromorphic processor. Each neurosynaptic core can be configured to act as either an encoding neuron or as a processing neuron, chosen to be Leaky-Integrate-and-Fire (LIF). We have also implemented a 1-1 software code for the processor, in which Pytorch and SNNtorch are used to build the spiking neural network, and surrogate gradients are used for training. An image classification task is used to evaluate the performance of the neuromorphic processor using the MNIST dataset, achieving an accuracy of 96.12% for 4-bit quantized synaptic weights. Implemented using GF22nmFDX technology, the processor is 0.72mm(2) in area, of which synaptic memories occupy 68% of the area, and achieves an average power efficiency of 14.8 nJ/SOP. This large area is justified by the configuration flexibility of the processor, where each neuron can be connected to any other. This allows the mapping of different and more sophisticated tasks.

关键词： Leaky-Integrate-and-Fire Neuromorphic Computing rate coding Spiking Neural Networks (SNNs)

来源：评论

学校读者我要写书评

暂无评论

Functional Connectivity Analysis from Multi Spike Trains on Prefrontal Cortex of Rat during Working Memory Task

Functional Connectivity Analysis from Multi Spike Trains on ...

引用

5th International Symposium on Computational Intelligence and Design (ISCID)

作者： Qi, Dexuan Xiao, Zhenguo Tian, Xin Tianjin Med Univ Tianjin Res Ctr Basic Med Sci Tianjin Peoples R China

ISBN: (纸本)9780769548111;9781467326469

Functional connectivity networks on prefrontal cortex of rat during working memory task are analyzed. Neural ensemble rate coding is applied to find the time interval of working memory event occurrence. The analysis of functional connectivity is carried out though the method of cross-covariance. Functional connectivity networks during the occurrence of working memory event and the period of resting state are obtained. The two networks satisfy the small-world network property. Degree centralities of vertexes within two networks are calculated to find important neuron. And the results are agreed with neural ensemble rate coding.

关键词： functional connectivity neural ensemble rate coding spike trains working memory small-world network

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：