DeepAI AI Chat
Log In Sign Up

Genetic Network Architecture Search

by   Hai Victor Habi, et al.
Tel Aviv University

We propose a method for learning the neural network architecture that based on Genetic Algorithm (GA). Our approach uses a genetic algorithm integrated with standard Stochastic Gradient Descent(SGD) which allows the sharing of weights across all architecture solutions. The method uses GA to design a sub-graph of Convolution cell which maximizes the accuracy on the validation-set. Through experiments, we demonstrate this methods performance on both CIFAR10 and CIFAR100 dataset with an accuracy of 96 and result of this work available in GitHub:


Parameter-less Optimization with the Extended Compact Genetic Algorithm and Iterated Local Search

This paper presents a parameter-less optimization framework that uses th...

GAAF: Searching Activation Functions for Binary Neural Networks through Genetic Algorithm

Binary neural networks (BNNs) show promising utilization in cost and pow...

PyGAD: An Intuitive Genetic Algorithm Python Library

This paper introduces PyGAD, an open-source easy-to-use Python library f...

Genetic Algorithm for More Efficient Multi-layer Thickness Optimization in Solar Cell

We propose to use Genetic Algorithm (GA), inspired by Darwin's evolution...

Genetic Algorithm-Based Solver for Very Large Multiple Jigsaw Puzzles of Unknown Dimensions and Piece Orientation

In this paper we propose the first genetic algorithm (GA)-based solver f...

Forest structure in epigenetic landscapes

Morphogenesis is the biological process that causes the emergence and ch...

Code Repositories


The genetic neural architecture search (GeneticNAS) is a neural architecture search method that is based on genetic algorithm which utilized weight sharing across all candidate network.

view repo