Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Deep unsupervised learning using spike-timing-dependent plasticity

Journal Article · · Neuromorphic Computing and Engineering
;
Abstract

Spike-timing-dependent plasticity (STDP) is an unsupervised learning mechanism for spiking neural networks that has received significant attention from the neuromorphic hardware community. However, scaling such local learning techniques to deeper networks and large-scale tasks has remained elusive. In this work, we investigate a Deep-STDP framework where a rate-based convolutional network, that can be deployed in a neuromorphic setting, is trained in tandem with pseudo-labels generated by the STDP clustering process on the network outputs. We achieve 24.56% higher accuracy and 3.5 × faster convergence speed at iso-accuracy on a 10-class subset of the Tiny ImageNet dataset in contrast to a k -means clustering approach.

Sponsoring Organization:
USDOE
Grant/Contract Number:
SC0021562
OSTI ID:
2345948
Alternate ID(s):
OSTI ID: 2333701
Journal Information:
Neuromorphic Computing and Engineering, Journal Name: Neuromorphic Computing and Engineering Journal Issue: 2 Vol. 4; ISSN 2634-4386
Publisher:
IOP PublishingCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (23)

Artificial Neural Network (ANN) to Spiking Neural Network (SNN) Converters Based on Diffusive Memristors journal November 2018
A recommender system using GA K-means clustering in an online shopping market journal February 2008
EqSpike: Spike-driven equilibrium propagation for neuromorphic implementations journal March 2021
Learning representations by back-propagating errors journal October 1986
Intrinsic synaptic plasticity of ferroelectric field effect transistors for online learning journal September 2021
Genetic K-means algorithm journal June 1999
Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook journal May 2021
The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web] journal October 2012
Event-Driven Continuous STDP Learning With Deep Structure for Visual Pattern Recognition journal April 2019
Least squares quantization in PCM journal March 1982
Reducing the Dimensionality of Data with Neural Networks journal July 2006
Spike Timing–Dependent Plasticity: A Hebbian Learning Rule journal July 2008
Unsupervised learning of digit recognition using spike-timing-dependent plasticity journal August 2015
Equilibrium Propagation: Bridging the Gap between Energy-Based Models and Backpropagation journal May 2017
Unsupervised Feature Learning With Winner-Takes-All Based STDP journal April 2018
BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python journal December 2018
Event-driven contrastive divergence for spiking neuromorphic systems journal January 2014
Training Deep Spiking Convolutional Neural Networks With STDP-Based Unsupervised Pre-training Followed by Supervised Fine-Tuning journal August 2018
Going Deeper in Spiking Neural Networks: VGG and Residual Architectures journal March 2019
Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE) journal May 2020
Exploring the Connection Between Binary and Spiking Neural Networks journal June 2020
Neuroevolution Guided Hybrid Spiking Neural Network Training journal April 2022
High-accuracy deep ANN-to-SNN conversion using quantization-aware training framework and calcium-gated bipolar leaky integrate and fire neuron journal March 2023

Similar Records

Experimental Demonstration of Ferroelectric Spiking Neurons for Unsupervised Clustering
Conference · Tue Jan 15 23:00:00 EST 2019 · OSTI ID:1637288
Training Spiking Neural Networks with Synaptic Plasticity under Integer Representation
Conference · Thu Jul 01 00:00:00 EDT 2021 · OSTI ID:1876349

Related Subjects