A simple workflow for deep learning

As a follow-up to my Primer On Universal Function Approximation with Deep Learning, I’ve created a project on Github that provides a working example of building, training, and evaluating a neural network. Included are helper functions in Lua that I wrote to simplify creating the data and using some functional programming techniques. The basic workflow for the example is this: Create/acquire a training set; Analyze the data for traits, distributions, noise, etc.; Design a deep learning architecture including the layers and activation functions. Also make sure you understand the type of problem you are trying to solve); Choose hyper parameters, such as cost function, optimizer, and learning rate; Train the model; Evaluate in-sample and out-of-sample performance. My personal preference is to limit the use of a deep learning framework to…


Link to Full Article: A simple workflow for deep learning