Bayesian Optimization Hands-on with Python Colab

In this video, I present the hand-on of Bayesian optimization (BayesOpt) using Google Colab. Using BayesOpt we can learn the optimal structure of the deep neural network. It is very difficult to figure out the optimal number of layers and the number of nodes in each layer. BayesOpt is a derivative-free optimal sequentially design optimization strategy that tries to find the global optima and doesn't get stuck to a local optimum.

We use the Bayesian Optimization module by Thomas Huijskens.