Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting

2010 ◽  
Vol 22 (2) ◽  
pp. 467-510 ◽  
Author(s):  
Filip Ponulak ◽  
Andrzej Kasiński
Keyword(s):  
Supervised Learning ◽  
Fundamental Property ◽  
Learning Rule ◽  
Relevant Information ◽  
Spiking Neurons ◽  
Time Shift ◽  
Surprising Result ◽  
Daily Routines ◽  
Input Signals ◽  
Target Templates

Learning from instructions or demonstrations is a fundamental property of our brain necessary to acquire new knowledge and develop novel skills or behavioral patterns. This type of learning is thought to be involved in most of our daily routines. Although the concept of instruction-based learning has been studied for several decades, the exact neural mechanisms implementing this process remain unrevealed. One of the central questions in this regard is, How do neurons learn to reproduce template signals (instructions) encoded in precisely timed sequences of spikes? Here we present a model of supervised learning for biologically plausible neurons that addresses this question. In a set of experiments, we demonstrate that our approach enables us to train spiking neurons to reproduce arbitrary template spike patterns in response to given synaptic stimuli even in the presence of various sources of noise. We show that the learning rule can also be used for decision-making tasks. Neurons can be trained to classify categories of input signals based on only a temporal configuration of spikes. The decision is communicated by emitting precisely timed spike trains associated with given input categories. Trained neurons can perform the classification task correctly even if stimuli and corresponding decision times are temporally separated and the relevant information is consequently highly overlapped by the ongoing neural activity. Finally, we demonstrate that neurons can be trained to reproduce sequences of spikes with a controllable time shift with respect to target templates. A reproduced signal can follow or even precede the targets. This surprising result points out that spiking neurons can potentially be applied to forecast the behavior (firing times) of other reference neurons or networks.

scholarly journals Improved SpikeProp for Using Particle Swarm Optimization

2013 ◽  
Vol 2013 ◽  
pp. 1-13 ◽  
Author(s):  
Falah Y. H. Ahmed ◽  
Siti Mariyam Shamsuddin ◽  
Siti Zaiton Mohd Hashim
Keyword(s):  
Particle Swarm Optimization ◽  
Supervised Learning ◽  
Learning Algorithm ◽  
Particle Swarm ◽  
Learning Rule ◽  
Temporal Coding ◽  
Spiking Neurons ◽  
Learning Enhancement ◽  
Swarm Optimization ◽  
Spiking Networks

A spiking neurons network encodes information in the timing of individual spike times. A novel supervised learning rule for SpikeProp is derived to overcome the discontinuities introduced by the spiking thresholding. This algorithm is based on an error-backpropagation learning rule suited for supervised learning of spiking neurons that use exact spike time coding. The SpikeProp is able to demonstrate the spiking neurons that can perform complex nonlinear classification in fast temporal coding. This study proposes enhancements of SpikeProp learning algorithm for supervised training of spiking networks which can deal with complex patterns. The proposed methods include the SpikeProp particle swarm optimization (PSO) and angle driven dependency learning rate. These methods are presented to SpikeProp network for multilayer learning enhancement and weights optimization. Input and output patterns are encoded as spike trains of precisely timed spikes, and the network learns to transform the input trains into target output trains. With these enhancements, our proposed methods outperformed other conventional neural network architectures.

A New Supervised Learning Algorithm for Spiking Neurons

2013 ◽  
Vol 25 (6) ◽  
pp. 1472-1511 ◽  
Author(s):  
Yan Xu ◽  
Xiaoqin Zeng ◽  
Shuiming Zhong
Keyword(s):  
Supervised Learning ◽  
Learning Algorithm ◽  
Learning Rule ◽  
Classification Problem ◽  
Higher Learning ◽  
Spiking Neurons ◽  
Spiking Neuron ◽  
Temporal Encoding ◽  
The Times ◽  
Perceptron Learning

The purpose of supervised learning with temporal encoding for spiking neurons is to make the neurons emit a specific spike train encoded by the precise firing times of spikes. If only running time is considered, the supervised learning for a spiking neuron is equivalent to distinguishing the times of desired output spikes and the other time during the running process of the neuron through adjusting synaptic weights, which can be regarded as a classification problem. Based on this idea, this letter proposes a new supervised learning method for spiking neurons with temporal encoding; it first transforms the supervised learning into a classification problem and then solves the problem by using the perceptron learning rule. The experiment results show that the proposed method has higher learning accuracy and efficiency over the existing learning methods, so it is more powerful for solving complex and real-time problems.

scholarly journals Biologically plausible learning in a deep recurrent spiking network

2019 ◽  
Author(s):  
David Rotermund ◽  
Klaus R. Pawelzik
Keyword(s):  
Large Scale ◽  
Fundamental Property ◽  
Learning Rule ◽  
Spike Timing ◽  
Spiking Neurons ◽  
Global Network ◽  
Large Network ◽  
Deep Networks ◽  
Local Circuits ◽  
The Brain

AbstractArtificial deep convolutional networks (DCNs) meanwhile beat even human performance in challenging tasks. Recently DCNs were shown to also predict real neuronal responses. Their relevance for understanding the neuronal networks in the brain, however, remains questionable. In contrast to the unidirectional architecture of DCNs neurons in cortex are recurrently connected and exchange signals by short pulses, the action potentials. Furthermore, learning in the brain is based on local synaptic mechanisms, in stark contrast to the global optimization methods used in technical deep networks. What is missing is a similarly powerful approach with spiking neurons that employs local synaptic learning mechanisms for optimizing global network performance. Here, we present a framework consisting of mutually coupled local circuits of spiking neurons. The dynamics of the circuits is derived from first principles to optimally encode their respective inputs. From the same global objective function a local learning rule is derived that corresponds to spike-timing dependent plasticity of the excitatory inter-circuit synapses. For deep networks built from these circuits self-organization is based on the ensemble of inputs while for supervised learning the desired outputs are applied in parallel as additional inputs to output layers.Generality of the approach is shown with Boolean functions and its functionality is demonstrated with an image classification task, where networks of spiking neurons approach the performance of their artificial cousins. Since the local circuits operate independently and in parallel, the novel framework not only meets a fundamental property of the brain but also allows for the construction of special hardware. We expect that this will in future enable investigations of very large network architectures far beyond current DCNs, including also large scale models of cortex where areas consisting of many local circuits form a complex cyclic network.

A Spiking Neuron as Information Bottleneck

2010 ◽  
Vol 22 (8) ◽  
pp. 1961-1992 ◽  
Author(s):  
Lars Buesing ◽  
Wolfgang Maass
Keyword(s):  
Spike Train ◽  
Contextual Information ◽  
Learning Rule ◽  
Relevant Information ◽  
Spiking Neurons ◽  
Single Output ◽  
Information Bottleneck ◽  
Plausible Model ◽  
Output Spike ◽  
Input Spike

Neurons receive thousands of presynaptic input spike trains while emitting a single output spike train. This drastic dimensionality reduction suggests considering a neuron as a bottleneck for information transmission. Extending recent results, we propose a simple learning rule for the weights of spiking neurons derived from the information bottleneck (IB) framework that minimizes the loss of relevant information transmitted in the output spike train. In the IB framework, relevance of information is defined with respect to contextual information, the latter entering the proposed learning rule as a “third” factor besides pre- and postsynaptic activities. This renders the theoretically motivated learning rule a plausible model for experimentally observed synaptic plasticity phenomena involving three factors. Furthermore, we show that the proposed IB learning rule allows spiking neurons to learn a predictive code, that is, to extract those parts of their input that are predictive for future input.

scholarly journals Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning

2019 ◽  
Author(s):  
Bingbing Xu ◽  
Huawei Shen ◽  
Qi Cao ◽  
Keting Cen ◽  
Xueqi Cheng
Keyword(s):  
Heat Kernel ◽  
Supervised Learning ◽  
Low Frequency ◽  
Weighted Average ◽  
Relevant Information ◽  
Semisupervised Learning ◽  
Heat Diffusion ◽  
Graph Structure ◽  
Convolutional Networks ◽  
Benchmark Datasets

Graph convolutional networks gain remarkable success in semi-supervised learning on graph-structured data. The key to graph-based semisupervised learning is capturing the smoothness of labels or features over nodes exerted by graph structure. Previous methods, spectral methods and spatial methods, devote to defining graph convolution as a weighted average over neighboring nodes, and then learn graph convolution kernels to leverage the smoothness to improve the performance of graph-based semi-supervised learning. One open challenge is how to determine appropriate neighborhood that reflects relevant information of smoothness manifested in graph structure. In this paper, we propose GraphHeat, leveraging heat kernel to enhance low-frequency filters and enforce smoothness in the signal variation on the graph. GraphHeat leverages the local structure of target node under heat diffusion to determine its neighboring nodes flexibly, without the constraint of order suffered by previous methods. GraphHeat achieves state-of-the-art results in the task of graph-based semi-supervised classification across three benchmark datasets: Cora, Citeseer and Pubmed.

scholarly journals Complex spike clusters and false‐positive rejection in a cerebellar supervised learning rule

2019 ◽  
Vol 597 (16) ◽  
pp. 4387-4406 ◽  
Author(s):  
Heather K. Titley ◽  
Mikhail Kislin ◽  
Dana H. Simmons ◽  
Samuel S.‐H. Wang ◽  
Christian Hansel
Keyword(s):  
Supervised Learning ◽  
False Positive ◽  
Learning Rule ◽  
Complex Spike

scholarly journals Predicting Surgical Phases using CNN-NARX Neural Network

2019 ◽  
Vol 5 (1) ◽  
pp. 405-407
Author(s):  
Nour Aldeen Jalal ◽  
Tamer Abdulbaki Alshirbaji ◽  
Knut Möller
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Relevant Information ◽  
Surgical Tools ◽  
Use Of Data ◽  
Input Signals ◽  
Phase Prediction ◽  
Context Aware System ◽  
Laparoscopic Videos ◽  
Narx Neural Network

AbstractOnline recognition of surgical phases is essential to develop systems able to effectively conceive the workflow and provide relevant information to surgical staff during surgical procedures. These systems, known as context-aware system (CAS), are designed to assist surgeons, improve scheduling efficiency of operating rooms (ORs) and surgical team and promote a comprehensive perception and awareness of the OR. State-of-the-art studies for recognizing surgical phases have made use of data from different sources such as videos or binary usage signals from surgical tools. In this work, we propose a deep learning pipeline, namely a convolutional neural network (CNN) and a nonlinear autoregressive network with exogenous inputs (NARX), designed to predict surgical phases from laparoscopic videos. A convolutional neural network (CNN) is used to perform the tool classification task by automatically learning visual features from laparoscopic videos. The output of the CNN, which represents binary usage signals of surgical tools, is provided to a NARX neural network that performs a multistep-ahead predictions of surgical phases. Surgical phase prediction performance of the proposed pipeline was evaluated on a dataset of 80 cholecystectomy videos (Cholec80 dataset). Results show that the NARX model provides a good modelling of the temporal dependencies between surgical phases. However, more input signals are needed to improve the recognition accuracy.

Sign in / Sign up

Export Citation Format

Share Document