Event Camera Data Classification Using Spiking Networks with Spike-Timing-Dependent Plasticity
Authors:
- 18 July 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
We present an optimization-based theory describing spiking cortical ensembles equipped with Spike-Timing-Dependent Plasticity (STDP) learning, as empirically observed in the visual cortex. Using this generic framework, we build a class of global and action-based feature descriptors for event-based cameras that we assess on the N-MNIST and the IBM DVS128 Gesture datasets. We report significant accuracy improvements compared to state-of-the-art STDP-based systems (+9.3% on N-MNIST, +7.74% on IBM DVS128 Gesture). In addition to ultra-low-power learning in neuromorphic edge devices, our work contributes towards a biologically-plausible, optimization-based theory of cortical vision.Keywords
This publication has 19 references indexed in Scilit:
- Self-organizing neurons: toward brain-inspired unsupervised learning2019
- DART: Distribution Aware Retinal Transform for Event-based CamerasIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Mastering the Output Frequency in Spiking Neural Networks2018
- HATS: Histograms of Averaged Time Surfaces for Robust Event-Based Object Classification2018
- A Low Power, Fully Event-Based Gesture Recognition System2017
- Converting Static Image Datasets to Spiking Neuromorphic Datasets Using SaccadesFrontiers in Neuroscience, 2015
- Dictionary Learning for Sparse Coding: Algorithms and Convergence AnalysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Sparse Coding via Thresholding and Local Competition in Neural CircuitsNeural Computation, 2008
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraintCommunications on Pure and Applied Mathematics, 2004