From the course: Deep Learning: Getting Started
Join today to access over 25,900 courses taught by industry experts.
Setup and initialization
From the course: Deep Learning: Getting Started
Setup and initialization
How does a deep learning model get trained? We will explore this process in detail in this chapter. We will start with setup and initialization for the training process in this video. Before we start training the neural network, the training input data needs to be prepared. The input data set contains a number of samples with each sample having a list of features. This training dataset goes through several transformations during input preprocessing. This includes applying a number of preprocessing techniques to convert samples into numeric vectors. They are then transposed optionally to create the input vectors. The target variables may also undergo several transformations. To help with training, the input data is usually split into training, test, and validation sets. This allows us to train the model, tune it, and finally evaluate it on the data it has never seen before. A training dataset is used to run through the neural network and fit the parameters like weights and biases. This…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
