A Genetic Deep Learning Model for Electrophysiological Soft Robotics

Hari Pandey, David Windridge

Research output: Chapter in Book/Report/Conference proceedingConference proceeding (ISBN)

28 Downloads (Pure)

Abstract

Deep learning methods are modeled by means of multiple layers of predefined set of operations. These days, deep learning techniques utilizing unsupervised learning for training neural networks layers have shown effective results in various fields. Genetic algorithms, by contrast, are search and optimization algorithm that mimic evolutionary process. Previous scientific literatures reveal that genetic algorithms have been successfully implemented for training three-layer neural networks. In this paper, we propose a novel genetic approach to evolving deep learning networks. The performance of the proposed method is evaluated in the context of an electrophysiological soft robot like system, the results of which demonstrate that our proposed hybrid system is capable of effectively training a deep learning network.
Original languageEnglish
Title of host publicationNot Known
Publication statusAccepted/In press - 24 Jun 2018
Event8th International Workshop on Soft Computing Applications - Arad, Romania
Duration: 13 Sep 201815 Sep 2018

Conference

Conference8th International Workshop on Soft Computing Applications
CountryRomania
CityArad
Period13/09/1815/09/18

Keywords

  • Deep learning
  • Evolutionary algorithm
  • Genetic algorithm
  • Metaheuristics
  • Neural networks

Fingerprint Dive into the research topics of 'A Genetic Deep Learning Model for Electrophysiological Soft Robotics'. Together they form a unique fingerprint.

  • Cite this

    Pandey, H., & Windridge, D. (Accepted/In press). A Genetic Deep Learning Model for Electrophysiological Soft Robotics. In Not Known