Filters








16,320 Hits in 4.6 sec

Supervised Learning In Spiking Neural Networks For Precise Temporal Encoding

Brian Gardner, Eric Nichols, Andre Gruning
2016 Zenodo  
Presentation given at the Kirchhoff-Institute at University of Heidelberg.  ...  The network contained a single readout neuron, trained under either the INST or FILT rule. The number of epochs corresponds to the time taken to reach a 90 % performance level.  ...  learn to encode spatio-temporal patterns as precisely timed spikes. has a strong theoretical basis. respects biology in real neural networks.  ... 
doi:10.5281/zenodo.61715 fatcat:vfe4j4mhaja53k7lwgoadx2vky

Error-backpropagation in temporally encoded networks of spiking neurons

Sander M. Bohte, Joost N. Kok, Han La Poutré
2002 Neurocomputing  
For a network of spiking neurons that encodes information in the timing of individual spike times, we derive a supervised learning rule, SpikeProp, akin to traditional errorbackpropagation.  ...  Comparing the (implicit) number of spiking neurons required for the encoding of the interpolated XOR problem, the trained networks demonstrate that temporal coding is a viable code for fast neural information  ...  Given the explicit use of the time domain for calculations, we believe that a network of spiking neurons is intrinsically more suited for learning and evaluating temporal patterns than sigmoidal networks  ... 
doi:10.1016/s0925-2312(01)00658-0 fatcat:3w3wojoyvnbupbtyyf4nsckqee

Evaluating SPAN Incremental Learning for Handwritten Digit Recognition [chapter]

Ammar Mohemmed, Guoyu Lu, Nikola Kasabov
2012 Lecture Notes in Computer Science  
The algorithm trains a neuron to associate target spike patterns to input spatio-temporal spike patterns.  ...  In a previous work [12, 11] , the authors proposed SPAN: a learning algorithm based on temporal coding for Spiking Neural Network (SNN).  ...  This work is supported by the Knowledge Engineering and Discovery Research Institute (www.kedri.info) of Auckland University of Technology.  ... 
doi:10.1007/978-3-642-34487-9_81 fatcat:mv7mwthu45cq5gdjbiuouz6neu

Spatio-temporal Spike Pattern Classification in Neuromorphic Systems [chapter]

Sadique Sheik, Michael Pfeiffer, Fabio Stefanini, Giacomo Indiveri
2013 Lecture Notes in Computer Science  
Such systems typically comprise event-based sensors and multi-neuron chips that encode, transmit, and process signals using spikes.  ...  In this paper we evaluate the computational approaches that have been proposed for classifying spatio-temporal sequences of spike-trains, derive the main principles and the key components that are required  ...  A detailed analysis of what type of patterns neurons can learn through STDP is presented in [20] .  ... 
doi:10.1007/978-3-642-39802-5_23 fatcat:p2q6das46reefacqzdj7qp6ay4

PT-Spike: A Precise-Time-Dependent Single Spike Neuromorphic Architecture with Efficient Supervised Learning [article]

Tao Liu, Lei Jiang, Yier Jin, Gang Quan, Wujie Wen
2018 arXiv   pre-print
Three constituent hardware-favorable techniques: precise single-spike temporal encoding, efficient supervised temporal learning, and fast asymmetric decoding are proposed accordingly to boost the energy  ...  The third generation of neural network model--Spiking Neural Network (SNN), inspired by the working mechanism and efficiency of human brain, has emerged as a promising solution for achieving more impressive  ...  For example, neuron Ni only engages in the synaptic plasticity of pattern Pi and will be ignored during the learning of all other patterns.  ... 
arXiv:1803.05109v1 fatcat:tuve33w7zbaflcudfav7geh75a

Unsupervised clustering with spiking neurons by sparse temporal coding and multilayer RBF networks

S.M. Bohte, H. La Poutre, J.N. Kok
2002 IEEE Transactions on Neural Networks  
We demonstrate that spiking neural networks encoding information in spike times are capable of computing and learning clusters from realistic data.  ...  We develop a temporal encoding of continuously valued data to obtain adjustable clustering capacity and precision with an efficient use of neurons: input variables are encoded in a population code by neurons  ...  Encoding continuous input variables in spike-times To extend the encoding precision and clustering capacity, we introduce a method for encoding inputdata into temporal spike-time patterns by population  ... 
doi:10.1109/72.991428 pmid:18244443 fatcat:aezwugdd2veblcxwjhsktloluu

FPT-spike: a flexible precise-time-dependent single-spike neuromorphic computing architecture

Tao Liu, Gang Quan, Wujie Wen
2020 CCF Transactions on High Performance Computing  
"FPT-spike" relies on three hardware-favorable components: precise ultra-sparse spike temporal encoding, efficient supervised temporal learning and fast asymmetric decoding, to realize flexible spatial-temporal  ...  On the other hand, the potentials of time-based SNN are not fully unleashed in real applications due to lack of efficient coding and practical learning schemes in temporal domain.  ...  We hope our study can inspire and motivate more in-depth research on the time-based SNN for realistic applications in energy-constraint platforms.  ... 
doi:10.1007/s42514-020-00037-6 fatcat:2hevpn5brfealictsg2vupzc6i

Error-Backpropagation in Networks of Fractionally Predictive Spiking Neurons [chapter]

Sander M. Bohte
2011 Lecture Notes in Computer Science  
We develop a learning rule for networks of spiking neurons where signals are encoded using fractionally predictive spike-coding.  ...  Here, we present an error-backpropagation algorithm to learn decoding these filters, and we show that networks of fractionally predictive spiking neurons can then implement temporal filters such as delayed  ...  (A)-(D): the output neuron in a 2-4-1 network correctly learns the spike-responsesŷptq to the four input-output patterns (inset boxes), in about 2000 epochs.  ... 
doi:10.1007/978-3-642-21735-7_8 fatcat:mialaxzgbjagxfobkzvzsewnua

Implementing Signature Neural Networks with Spiking Neurons

José Luis Carrillo-Medina, Roberto Latorre
2016 Frontiers in Computational Neuroscience  
The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces.  ...  To the best of our knowledge, none of these mechanisms have been used yet in the context of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicability in such networks.  ...  Spike-Timing Encoding Modality The spike-timing encoding is related to the spreading of specific intraburst spike patterns through the network and the synchronization mechanisms that allow a group of neurons  ... 
doi:10.3389/fncom.2016.00132 pmid:28066221 pmcid:PMC5167754 fatcat:mamchuc63baqppe5mb3rdak46i

A Deep 2-Dimensional Dynamical Spiking Neuronal Network for Temporal Encoding trained with STDP [article]

Matthew Evanusa and Cornelia Fermuller and Yiannis Aloimonos
2020 arXiv   pre-print
Spiking Neural Networks (SNNs) can be trained using biologically-realistic learning mechanisms, and can have neuronal activation rules that are biologically relevant.  ...  We argue that the randomness inherent in the network weights allow the neurons to form groups that encode the temporal data being inputted after self-organizing with STDP.  ...  Greg Davis and Jesse Milzman at the University of Maryland for thoughtful conversation and advice.  ... 
arXiv:2009.00581v1 fatcat:elshjencaffilgratq2uh5ran4

File Classification Based on Spiking Neural Networks [article]

Ana Stanojevic, Giovanni Cherubini, Timoleon Moraitis, Abu Sebastian
2020 arXiv   pre-print
File information contained in key-value metadata pairs is mapped by a novel correlative temporal encoding scheme to spike patterns that are input to an SNN.  ...  In this paper, we propose a system for file classification in large data sets based on spiking neural networks (SNNs).  ...  An example of encoding in SNN: (a) input spike pattern for all input neurons and (b) output spike pattern for one output neuron. Fig. 4 . 4 Fig. 4.  ... 
arXiv:2004.03953v1 fatcat:mang6ww725hxldeojltbbjqjzy

Dynamic Spatiotemporal Pattern Recognition with Recurrent Spiking Neural Network

Jiangrong Shen, Jian K. Liu, Yueming Wang
2021 Neural Computation  
Our model is a cascaded network with three layers of spiking neurons where the input and output layers are the encoder and decoder, respectively.  ...  Our real-time actions in everyday life reflect a range of spatiotemporal dynamic brain activity patterns, the consequence of neuronal computation with spikes in the brain.  ...  Acknowledgments This work was partly supported by the grants from the National Key R&D Program of China (2018YFA0701400), Zhejiang Lab (2019KE0AD01), Zhejiang Lab (2019KC0AB03 and 2019KC0AD02), the Royal  ... 
doi:10.1162/neco_a_01432 pmid:34474470 fatcat:rghtrhi6ondv7lg7cfrshev424

Deep Learning In Spiking Neural Networks

Kasabov
2018 Zenodo  
This is presentation at the HBP Workshop in Paris.  ...  Encoding of input data: Input data is encoded into spike sequences reflecting on the temporal changes in the data using some of the encoding algorithms, e.g. ( ref ) .  ...  Obtaining dynamic, functional patterns in the SNN model: A functional, dynamic pattern is revealed as a sequence of spiking activity of clusters of neurons in the SNN model that represent active functional  ... 
doi:10.5281/zenodo.1218147 fatcat:gwjr6fvup5bxjml2vsoe3kpuya

SpikeTemp: An Enhanced Rank-Order-Based Learning Approach for Spiking Neural Networks With Adaptive Structure

Jinling Wang, Ammar Belatreche, Liam P. Maguire, Thomas Martin McGinnity
2017 IEEE Transactions on Neural Networks and Learning Systems  
The trained feed-forward SNN consists of two layers of spiking neurons: an encoding layer which temporally encodes real valued features into spatio-temporal spike patterns, and an output layer of dynamically  ...  In addition, the number of output neurons is much smaller when the square cosine encoding scheme is employed.  ...  The neurons in the encoding layer temporally encode real valued feature vectors into spatio-temporal spike patterns, and output neurons, which process spatio-temporal inputs from the encoding layer, are  ... 
doi:10.1109/tnnls.2015.2501322 pmid:26642460 fatcat:o55uxxjnffd3vdldjci6e4yf4m

Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding

Brian Gardner, André Grüning, Maurice J. Chacron
2016 PLoS ONE  
We test the accuracy of the solutions provided by each rule with respect to their temporal encoding precision, and then measure the maximum number of input patterns they can learn to memorise using the  ...  For these reasons, much recent attention has been focused on the development of supervised learning rules for spiking neural networks that utilise a temporal coding scheme.  ...  Acknowledgments We are grateful to the reviewer Johanni Brea for his valuable comments, improving the quality of this paper. Author Contributions Conceptualization: BG AG. Data curation: BG AG.  ... 
doi:10.1371/journal.pone.0161335 pmid:27532262 pmcid:PMC4988787 fatcat:mnznc6phqbb3xft6atndub5k2e
« Previous Showing results 1 — 15 out of 16,320 results