February 2019
Beginner to intermediate
308 pages
7h 42m
English
In Chapter 1, Machine Learning and Neural Networks 101, we started off by building the simplest, one-layer neural network, known as the perceptron. At its core, the perceptron is simply a mathematical function that takes in a set of input, performs some mathematical computation, and outputs the result of the computation. For the perceptron, the mathematical computation is simply the multiplication of the weights with the inputs.
Therefore, the right set of weights dictates how well our neural network performs. At the start, the weights of the neural network are initialized randomly. The process of tuning the weights of our neural network to maximize model performance is called model training. During ...