Deep Convolutional Network: an Event-based approach

Research output: Conference proceeding/Chapter in Book/Report/Conference Paperpeer-review

Abstract

In this paper, we propose a methodology to incrementally compute a convolutional layer of a neural network based on events, and an architecture that can efficiently implement it. In order to illustrate the approach, we present an application example, where we train a traditional DNN based on a LeNet architecture using a traffic signs dataset and then, we replace the first convolutional layer with our event based approach.
Original languageEnglish
Title of host publication2021 Argentine Conference on Electronics - Congreso Argentino de Electronica 2021, CAE 2021
PublisherIEEE Computer Society
Pages50-54
Number of pages5
ISBN (Print)9781728175799
DOIs
Publication statusPublished - 12 Mar 2021
Event2021 Argentine Conference on Electronics (CAE) - Bahia Blanca, Argentina
Duration: 11 Mar 202112 Mar 2021

Publication series

Name2021 Argentine Conference on Electronics - Congreso Argentino de Electronica 2021, CAE 2021

Conference

Conference2021 Argentine Conference on Electronics (CAE)
Period11/03/2112/03/21

Keywords

  • Image resolution
  • Image recognition
  • Neural networks
  • Memory management
  • Standards
  • CNN
  • event-based imager
  • Deep Neural network

Fingerprint

Dive into the research topics of 'Deep Convolutional Network: an Event-based approach'. Together they form a unique fingerprint.

Cite this