Evolutionary Construction of Convolutional Neural Networks

by   Marijn van Knippenberg, et al.

Neuro-Evolution is a field of study that has recently gained significantly increased traction in the deep learning community. It combines deep neural networks and evolutionary algorithms to improve and/or automate the construction of neural networks. Recent Neuro-Evolution approaches have shown promising results, rivaling hand-crafted neural networks in terms of accuracy. A two-step approach is introduced where a convolutional autoencoder is created that efficiently compresses the input data in the first step, and a convolutional neural network is created to classify the compressed data in the second step. The creation of networks in both steps is guided by by an evolutionary process, where new networks are constantly being generated by mutating members of a collection of existing networks. Additionally, a method is introduced that considers the trade-off between compression and information loss of different convolutional autoencoders. This is used to select the optimal convolutional autoencoder from among those evolved to compress the data for the second step. The complete framework is implemented, tested on the popular CIFAR-10 data set, and the results are discussed. Finally, a number of possible directions for future work with this particular framework in mind are considered, including opportunities to improve its efficiency and its application in particular areas.


A Comparison of Deep Learning Classification Methods on Small-scale Image Data set: from Convolutional Neural Networks to Visual Transformers

In recent years, deep learning has made brilliant achievements in image ...

Optimizing Deep Neural Networks with Multiple Search Neuroevolution

This paper presents an evolutionary metaheuristic called Multiple Search...

Lamarckian Evolution of Convolutional Neural Networks

Convolutional neural networks belong to the most successul image classif...

Evolutionary Deep Nets for Non-Intrusive Load Monitoring

Non-Intrusive Load Monitoring (NILM) is an energy efficiency technique t...

DeepStreamCE: A Streaming Approach to Concept Evolution Detection in Deep Neural Networks

Deep neural networks have experimentally demonstrated superior performan...

Evolutionary Deep Learning to Identify Galaxies in the Zone of Avoidance

The Zone of Avoidance makes it difficult for astronomers to catalogue ga...

Please sign up or login with your details

Forgot password? Click here to reset