Hardware-amenable structural learning for spike-based pattern classification using a simple model of active dendrites

DOI10.1162/NECO_A_00713zbMATH Open1473.68150DBLPjournals/neco/HussainLB15arXiv1411.5881OpenAlexW2004159737WikidataQ50597929 ScholiaQ50597929MaRDI QIDQ5380229FDOQ5380229

Authors: Shaista Hussain, Shihchii Liu, Arindam Basu 

Publication date: 4 June 2019

Published in: Neural Computation (Search for Journal in Brave)

Abstract: This paper presents a spike-based model which employs neurons with functionally distinct dendritic compartments for classifying high dimensional binary patterns. The synaptic inputs arriving on each dendritic subunit are nonlinearly processed before being linearly integrated at the soma, giving the neuron a capacity to perform a large number of input-output mappings. The model utilizes sparse synaptic connectivity; where each synapse takes a binary value. The optimal connection pattern of a neuron is learned by using a simple hardware-friendly, margin enhancing learning algorithm inspired by the mechanism of structural plasticity in biological neurons. The learning algorithm groups correlated synaptic inputs on the same dendritic branch. Since the learning results in modified connection patterns, it can be incorporated into current event-based neuromorphic systems with little overhead. This work also presents a branch-specific spike-based version of this structural plasticity rule. The proposed model is evaluated on benchmark binary classification problems and its performance is compared against that achieved using Support Vector Machine (SVM) and Extreme Learning Machine (ELM) techniques. Our proposed method attains comparable performance while utilizing 10 to 50% less computational resources than the other reported techniques.

Full work available at URL: https://arxiv.org/abs/1411.5881

Recommendations

• Solving a classification task by spiking neural network with stdp based on rate and temporal input encoding
• Minimal spiking neuron for solving multilabel classification tasks
• scientific article; zbMATH DE number 1928727
• An unsupervised neuromorphic clustering algorithm
• Dynamic spatiotemporal pattern recognition with recurrent spiking neural network

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Neural networks for/in biological studies, artificial life and related topics (92B20)

Cites Work

• Title not available (Why is that?)
• Spiking Neuron Models
• Information Processing in Dendritic Trees
• Neuromorphic implementation of orientation hypercolumns
• Learning Real-World Stimuli in a Neural Network with Spike-Driven Synaptic Dynamics
• On the complexity of learning for spiking neurons with temporal coding.
• Synaptic Dynamics in Analog VLSI
• Point-to-point connectivity between neuromorphic chips using address events

Cited In (5)

• Classification of Correlated Patterns with a Configurable Analog VLSI Neural Network of Spiking Neurons and Self-Regulating Plastic Synapses
• Minimal spiking neuron for solving multilabel classification tasks
• An unsupervised neuromorphic clustering algorithm
• An automatic classification pipeline for the complex synaptic structure based on deep learning
• Title not available (Why is that?)

Uses Software

• UCI-ml

This page was built for publication: Hardware-amenable structural learning for spike-based pattern classification using a simple model of active dendrites

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380229)