scholarly journals Error-Backpropagation in Networks of Fractionally Predictive Spiking Neurons

2011 ◽  
pp. 60-68 ◽  
Author(s):  
Sander M. Bohte
Keyword(s):  
Spiking Neurons

scholarly journals Using a Low-Power Spiking Continuous Time Neuron (SCTN) for Sound Signal Processing

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1065
Author(s):  
Moshe Bensimon ◽  
Shlomo Greenberg ◽  
Moshe Haiut
Keyword(s):  
Neural Network ◽  
Network Structure ◽  
Analog Circuits ◽  
Continuous Time ◽  
Spiking Neurons ◽  
Spiking Neural Network ◽  
Sound Classification ◽  
Classification Framework ◽  
Neural Network Structure ◽  
Simple Analog

This work presents a new approach based on a spiking neural network for sound preprocessing and classification. The proposed approach is biologically inspired by the biological neuron’s characteristic using spiking neurons, and Spike-Timing-Dependent Plasticity (STDP)-based learning rule. We propose a biologically plausible sound classification framework that uses a Spiking Neural Network (SNN) for detecting the embedded frequencies contained within an acoustic signal. This work also demonstrates an efficient hardware implementation of the SNN network based on the low-power Spike Continuous Time Neuron (SCTN). The proposed sound classification framework suggests direct Pulse Density Modulation (PDM) interfacing of the acoustic sensor with the SCTN-based network avoiding the usage of costly digital-to-analog conversions. This paper presents a new connectivity approach applied to Spiking Neuron (SN)-based neural networks. We suggest considering the SCTN neuron as a basic building block in the design of programmable analog electronics circuits. Usually, a neuron is used as a repeated modular element in any neural network structure, and the connectivity between the neurons located at different layers is well defined. Thus, generating a modular Neural Network structure composed of several layers with full or partial connectivity. The proposed approach suggests controlling the behavior of the spiking neurons, and applying smart connectivity to enable the design of simple analog circuits based on SNN. Unlike existing NN-based solutions for which the preprocessing phase is carried out using analog circuits and analog-to-digital conversion, we suggest integrating the preprocessing phase into the network. This approach allows referring to the basic SCTN as an analog module enabling the design of simple analog circuits based on SNN with unique inter-connections between the neurons. The efficiency of the proposed approach is demonstrated by implementing SCTN-based resonators for sound feature extraction and classification. The proposed SCTN-based sound classification approach demonstrates a classification accuracy of 98.73% using the Real-World Computing Partnership (RWCP) database.

Pulse Inputs Affect Timings of Spikes in Neurons with or Without Time Delays

2019 ◽  
Vol 20 (3-4) ◽  
pp. 257-267
Author(s):  
Jiaoyan Wang ◽  
Xiaoshan Zhao ◽  
Chao Lei
Keyword(s):  
Time Delays ◽  
Single Neuron ◽  
Spiking Neurons ◽  
Phase Resetting ◽  
Subthreshold Oscillations ◽  
Weak Pulse

AbstractInputs can change timings of spikes in neurons. But it is still not clear how input’s parameters for example injecting time of inputs affect timings of neurons. HR neurons receiving both weak and strong inputs are considered. How pulse inputs affecting neurons is studied by using the phase-resetting curve technique. For a single neuron, weak pulse inputs may advance or delay the next spike, while strong pulse inputs may induce subthreshold oscillations depending on parameters such as injecting timings of inputs. The behavior of synchronization in a network with or without coupling delays can be predicted by analysis in a single neuron. Our results can be used to predict the effects of inputs on other spiking neurons.

Chaotic Liquid State Machine

2015 ◽  
Vol 9 (4) ◽  
pp. 1-20
Author(s):  
Mario Antoine Aoun ◽  
Mounir Boukadoum
Keyword(s):  
Liquid State ◽  
State Machine ◽  
Spiking Neurons ◽  
Signature Verification ◽  
Time Varying ◽  
Plasticity Mechanism ◽  
Online Signature ◽  
Online Signature Verification ◽  
One Class Classifier ◽  
Classification Capability

The authors implement a Liquid State Machine composed from a pool of chaotic spiking neurons. Furthermore, a synaptic plasticity mechanism operates on the connection weights between the neurons inside the pool. A special feature of the system's classification capability is that it can learn the class of a set of time varying inputs when trained from positive examples only, thus, it is a one class classifier. To demonstrate the applicability of this novel neurocomputing architecture, the authors apply it for Online Signature Verification.

scholarly journals Dynamically Reconfigurable Silicon Array of Spiking Neurons With Conductance-Based Synapses

2007 ◽  
Vol 18 (1) ◽  
pp. 253-265 ◽  
Author(s):  
R. Jacob Vogelstein ◽  
Udayan Mallik ◽  
Joshua T. Vogelstein ◽  
Gert Cauwenberghs
Keyword(s):  
Spiking Neurons ◽  
Dynamically Reconfigurable

Phase Selective Oscillations in Two Noise Driven Synaptically Coupled Spiking Neurons

2015 ◽  
Vol 25 (07) ◽  
pp. 1540005
Author(s):  
Ilya Prokin ◽  
Ivan Tyukin ◽  
Victor Kazantsev
Keyword(s):  
Numerical Simulations ◽  
Coupled System ◽  
External Noise ◽  
Noise Signal ◽  
Feedback Mechanism ◽  
Spike Timing ◽  
Spiking Neurons ◽  
Time Lags ◽  
Tuning Parameters ◽  
Synaptic Inputs

The work investigates the influence of spike-timing dependent plasticity (STDP) mechanisms on the dynamics of two synaptically coupled neurons driven by additive external noise. In this setting, the noise signal models synaptic inputs that the pair receives from other neurons in a larger network. We show that in the absence of STDP feedbacks the pair of neurons exhibit oscillations and intermittent synchronization. When the synapse connecting the neurons is supplied with a phase selective feedback mechanism simulating STDP, induced dynamics of spikes in the coupled system resembles a phase locked mode with time lags between spikes oscillating about a specific value. This value, as we show by extensive numerical simulations, can be set arbitrary within a broad interval by tuning parameters of the STDP feedback.

Sign in / Sign up

Export Citation Format

Share Document