Hand tuning convolutional neural networks (CNN) for performance optimization can be tedious. A novel approach using a genetic algorithm to automate CNN hyper-parameter adjustment is proposed. This ...

This is the code base for the paper Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm by Xueli Xiao, Ming Yan, Sunitha Basodi, Chunyan Ji, Yi Pan.

Preparation for Using Optimization Algorithms It is rare that a problem is submitted to an optimization algorithm "as is." By making a few changes in your problem, you can reduce its complexity, that ...

Convolutional neural networks (CNNs) have shown great potential in different real word application. Defining a suitable CNN architecture is vital for obtaining good performance. In this work we ...

pl-cnn An optimization algorithm for learning Piecewise Linear Convolutional Neural Networks. This is the implementation of the paper Trusting SVM for Piecewise Linear CNNs by Leonard Berrada, Andrew ...