Regularized Evolutionary Algorithm for Dynamic Neural Topology Search

by   Cristiano Saltori, et al.
Università di Trento

Designing neural networks for object recognition requires considerable architecture engineering. As a remedy, neuro-evolutionary network architecture search, which automatically searches for optimal network architectures using evolutionary algorithms, has recently become very popular. Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i.e., network architectures) and is therefore memory expensive. In this work, we propose a Regularized Evolutionary Algorithm with low memory footprint to evolve a dynamic image classifier. In details, we introduce novel custom operators that regularize the evolutionary process of a micro-population of 10 individuals. We conduct experiments on three different digits datasets (MNIST, USPS, SVHN) and show that our evolutionary method obtains competitive results with the current state-of-the-art.


page 1

page 2

page 3

page 4


Evolutionary-Neural Hybrid Agents for Architecture Search

Neural Architecture Search has recently shown potential to automate the ...

Sampled Training and Node Inheritance for Fast Evolutionary Neural Architecture Search

The performance of a deep neural network is heavily dependent on its arc...

Evolutionary Cell Aided Design for Neural Network Architectures

Mathematical theory shows us that multilayer feedforward Artificial Neur...

Coevolutionary Neural Population Models

We present a method for using neural networks to model evolutionary popu...

An Evolutionary Algorithm of Linear complexity: Application to Training of Deep Neural Networks

The performance of deep neural networks, such as Deep Belief Networks fo...

Limited Evaluation Evolutionary Optimization of Large Neural Networks

Stochastic gradient descent is the most prevalent algorithm to train neu...

Asynchronous Evolution of Deep Neural Network Architectures

Many evolutionary algorithms (EAs) take advantage of parallel evaluation...

Please sign up or login with your details

Forgot password? Click here to reset