Seminar: Implementing Object or Face Recognition based Combination of Deep Neural Network and Geneti

Songyuan Ji
M.Sc. Thesis Proposal
Supervisor: Dr. Minglun Gong & Dr. Yuanzhu Chen

Implementing Object or Face Recognition based Combination of Deep Neural Network and Genetic Algorithm

Department of Computer Science
Friday, January 29, 2016, 1:40 p.m., Room EN 2022


Abstract

In machine learning, a Convolutional Neural Network (CNN, or ConvNet) is a type of feed-forward
artificial neural network where the individual neurons are tiled in such a way that they respond to
overlapping regions in the visual field[1]. In the field of artificial intelligence, a genetic algorithm
(GA) is a search heuristic that mimics the process of natural selection. The objective of this research
is to study a new model using GA to optimize the CNN. This heuristic (also sometimes called a
metaheuristic) is routinely used to generate useful solutions to optimization and search problems.[1]
Genetic algorithms belong to the larger class of evolutionary algorithms (EA), which generate
solutions to optimization problems using techniques inspired by natural evolution, such as
inheritance, mutation, selection, and crossover. In this thesis, the combination method of
Convolutional Neural Network and Genetic Algorithm will be create and used in visual
recognition[1], and there will be different application and experimentation based various
requirement.

 

Contact

Department of Computer Science

230 Elizabeth Ave

St. John's, NL A1B 3X9 CANADA

Tel: (709) 864-2530

Fax: (709) 864-2552

becomestudent@mun.ca