An illustrated and intuitive information on how Neural Networks study
Welcome to Half 2 of the Deep Studying Illustrated collection. Within the earlier article (undoubtedly learn that first!), we coated how a neural community works and the way a skilled neural community makes predictions.
On this article, we’ll delve into the coaching course of and discover how a neural community learns.
📣 If you happen to haven’t learn my earlier articles, I extremely suggest you begin with my collection of articles masking the fundamentals of machine studying, particularly the one on Gradient Descent since you’ll discover that numerous the fabric coated there’s related right here.
Machine Studying Starter Pack
Let’s say we wish to create a neural community that predicts the day by day income of ice cream gross sales utilizing the options temperature and day of the week.
That is the (artificial) coaching dataset we’re utilizing:
To construct a neural community, as we realized within the earlier article, we have to first resolve on its structure. This contains figuring out the variety of hidden layers, the variety of neurons in every layer, and the activation operate of every neuron.
Let’s say we determined our structure is: 1 hidden layer with 2 neurons, and 1 output neuron, all utilizing the rectifier activation operate.
Terminology segue: Within the earlier article, we realized about utilizing subscripts to distinguish between totally different weights. We’re sticking with the identical conference right here, and as well as, we‘ll use superscripts to…
