This chapter will show you how to build a multilayer perceptron neural network for signal detection. We will first discuss the architecture of multilayer perceptron neural networks. Then we will cover how to prepare the data, how to decide on hidden layers and neurons, and how to train and evaluate the model.
The section on preparing the data will be important going forward as these deep learning models require data to be in particular formats in order to pass the data to the models. The hidden layer is the part of the neural network that separates it from other machine learning algorithms, and in this chapter, we will show you how to search for the optimal number of nodes in a hidden layer. In addition, over the course of this chapter, you will become much more familiar with the MXNet syntax, including the model training and evaluation...
