From the course: Deep Learning with Python: Hands-On Introduction to Deep Learning Models
Join today to access over 25,300 courses taught by industry experts.
How does a neural network learn? - Python Tutorial
From the course: Deep Learning with Python: Hands-On Introduction to Deep Learning Models
How does a neural network learn?
- [Instructor] Similar to other supervised machine learning models, we train artificial neural networks using data that includes a set of independent variables and a dependent variable. The objective is to have the neural network learn by modeling the relationship between sets of input signals, the independent variables and corresponding output signals that depend a variable. As a neuro network processes each set of input signals, it learns to predict the associated output accurately by strengthening or weakening the connections between neurons based on patterns observed in the training data. To do this, networks use a technique called back propagation, which involves iteratively adjusting the weights and biases that control how signals pass through the network. Each iterative training cycle in back propagation is known as an epoch and includes a forward phase and a backward phase. To illustrate how back propagation works, let's walk through a simple example of a neural network that…
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.