In this example a bayesian framework is defined to tune hyperparameter of a CNN using hyperopt library developed https://github.com/hyperopt Bayesian optimization is a seuential model-based approach to solving problems. In particular, we prescribe a prior belief over the possible objective functions and then sequentially refine this model as data are observed via our updated beliefs-given data-on the likely ojective function we are optimizing. https://www.cs.ox.ac.uk/people/nando.defreitas/publications/BayesOptLoop.pdf This blog summarises bayesian optimization very thoroughly. https://medium.com/vantageai/bringing-back-the-time-spent-on-hyperparameter-tuning-with-bayesian-optimisation-2e21a3198afb
The CNN is used to model fashion MNIST dataset.