An Event-Driven Categorization Model for AER Image Sensors Using Multispike Encoding and Learning

Rong Xiao

doi:10.1109/TNNLS.2019.2945630

An Event-Driven Categorization Model for AER Image Sensors Using Multispike Encoding and Learning

2020-09-01

35

PRE

AI

DOI：10.1109/TNNLS.2019.2945630

Original

Original request for help

Save

Abstract

En 中文

In this article, we present a systematic computational model to explore brain-based computation for object recognition. The model extracts temporal features embedded in address-event representation (AER) data and discriminates different objects by using spiking neural networks (SNNs). We use multispike encoding to extract temporal features contained in the AER data. These temporal patterns are then learned through the tempotron learning rule. The presented model is consistently implemented in a temporal learning framework, where the precise timing of spikes is considered in the feature-encoding and learning process. A noise-reduction method is also proposed by calculating the correlation of an event with the surrounding spatial neighborhood based on the recently proposed time-surface technique. The model evaluated on wide spectrum data sets (MNIST, N-MNIST, MNIST-DVS, AER Posture, and Poker Card) demonstrates its superior recognition performance, especially for the events with noise.

Keywords:

Feature extraction

Computational modeling

Biological neural networks

Image sensors

Data models

Object recognition

Visualization

Event-based vision

neuromorphic computing

object recognition

spiking neural networks (SNNs)

An Event-Driven Categorization Model for AER Image Sensors Using Multispike Encoding and Learning

Abstract

AI Summary

Journal

Organization