Variable Chromosome Genetic Algorithm for Structure Learning in Neural Networks to Imitate Human Brain

Applied Sciences

Sung-do Chi¹  Kang-moon Park²  Donghoon Shin³ 

[1] Development Korea, Advanced Driver Assistance Systems, Seoul 04637, Korea;Department of Computer Science, College of Natural Science, Republic of Korea Naval Academy, Changwon-si 51704, Korea;;Mercedes-Benz Research &

关键词: variable chromosome genetic algorithm;    deep learning;    structure learning;    artificial neural network;    neural architecture search;   

DOI  :  10.3390/app9153176

来源: DOAJ

【 摘 要 】

This paper proposes the variable chromosome genetic algorithm (VCGA) for structure learning in neural networks. Currently, the structural parameters of neural networks, i.e., number of neurons, coupling relations, number of layers, etc., have mostly been designed on the basis of heuristic knowledge of an artificial intelligence (AI) expert. To overcome this limitation, in this study evolutionary approach (EA) has been utilized to automatically generate the proper artificial neural network (ANN) structures. VCGA has a new genetic operation called a chromosome attachment. By applying the VCGA, the initial ANN structures can be flexibly evolved toward the proper structure. The case study applied to the typical exclusive or (XOR) problem shows the feasibility of our methodology. Our approach is differentiated with others in that it uses a variable chromosome in the genetic algorithm. It makes a neural network structure vary naturally, both constructively and destructively. It has been shown that the XOR problem is successfully optimized using a VCGA with a chromosome attachment to learn the structure of neural networks. Research on the structure learning of more complex problems is the topic of our future research.

【 授权许可】

Unknown