Using Cartesian Genetic Programming Approach with New Crossover Technique to Design Convolutional Neural Networks
Created by W.Langdon from
gp-bibliography.bib Revision:1.8098
- @Article{torabi:NPL,
-
author = "Ali Torabi and Arash Sharifi and Mohammad Teshnehlab",
-
title = "Using Cartesian Genetic Programming Approach with New
Crossover Technique to Design Convolutional Neural
Networks",
-
journal = "Neural Processing Letters",
-
year = "2023",
-
volume = "55",
-
pages = "5451--5471",
-
month = oct,
-
keywords = "genetic algorithms, genetic programming, Cartesian
Genetic Programming, ANN, Convolutional neural network,
Neural architecture search, Crossover, Multiple
sequence alignment",
-
ISSN = "1370-4621",
-
URL = "https://rdcu.be/ddL4Z",
-
URL = "http://link.springer.com/article/10.1007/s11063-022-11093-0",
-
DOI = "doi:10.1007/s11063-022-11093-0",
-
size = "21 pages",
-
abstract = "In image classification problems, Convolutional Neural
Networks (CNNs) are deep neural networks that include a
variety of different layers aimed at classifying
images. Until today, the most promising and
state-of-the-art method in image recognition tasks is
CNN. Tuning the deep network with a large number of
hyperparameters to maximize performance would be an
excruciating task that requires lots of time and
engineering efforts. To construct that high-performance
architecture, experts should go through a lot of trial
and error. Neural Architecture Search is a way to
automatically fabricate an accurate network
architecture. An evolutionary algorithm called
Cartesian Genetic Programming (CGP) with a new
crossover operation based on the multiple Sequence
Alignment algorithm is proposed in this paper to
construct an appropriate neural network without the
burden of building manually. This new method has a
remarkable improvement over a standard CGP only by
adding a crossover operator. The datasets for training
on the proposed method were CIFAR-10 and CIFAR-100. The
results show that it achieves a good balance between
accuracy and the number of trainable parameters
compared to the other state-of-the-art methods",
-
notes = "Department of Control Engineering, K.N. Toosi
University of Technology, Tehran, Iran",
- }
Genetic Programming entries for
Ali Torabi
Arash Sharifi
Mohammad Teshnehlab
Citations