Artificial Neural Networks Optimization using Genetic Algorithm with Python

Artificial Neural Networks Optimization using Genetic Algorithm with Python - Towards Data Science

In a previous tutorial titled “Artificial Neural Network Implementation using NumPy and Classification of the Fruits360 Image Dataset” available in my LinkedIn profile at this link, an artificial neural network (ANN) is created for classifying 4 classes of the Fruits360 image dataset. The source code used in this tutorial is available in my GitHub page.

This tutorial is also available at TowardsDataScience here.

A quick summary of this tutorial is extracting the feature vector (360 bins hue channel histogram) and reducing it to just 102 element by using a filter-based technique using the standard deviation. Later, the ANN is built from scratch using NumPy.

The ANN was not completely created as just the forward pass was made ready but there is no backward pass for updating the network weights. This is why the accuracy is very low and not exceeds 45%. The solution to this problem is using an optimization technique for updating the network weights. This tutorial uses the genetic algorithm (GA) for optimizing the network weights.

It is worth-mentioning that both the previous and this tutorial are based on my 2018 book cited as “Ahmed Fawzy Gad ‘Practical Computer Vision Applications Using Deep Learning with CNNs’. Dec. 2018, Apress, 978–1–4842–4167–7 “. The book is available at Springer at this link. You can find all details within this book.

The source code used in this tutorial is available in my GitHub page here.

https://towardsdatascience.com/artificial-neural-networks-optimization-using-genetic-algorithm-with-python-1fe8ed17733e