From the course: Neural Networks and Convolutional Neural Networks Essential Training
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Neural networks
From the course: Neural Networks and Convolutional Neural Networks Essential Training
Neural networks
- [Instructor] In the previous video, we saw some of the limitations of using a single perceptron, as the output is only a linear combination of the inputs, and how we need to introduce non-linearity into our network. One of the key questions then is how do we extend from going from a single neuron to a Neural Network. We will define a Multilayer Perceptron, as being one where the perceptrons are divided up into multiple layers. The output of a perceptron will be the input to another perceptron. You will see that this is a fully connected layer, and so each layer processes all of the outputs from the previous layer. Each of the perceptrons in the diagram behave like the single perceptron. The input is a linear combination of the sum the products of the weight times the input. The input to this perceptron is a linear combination of all of the outputs multiplied by weight, which I have indicated by Wij, of perceptrons of the previous layer. The output from this perceptron is connected…
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.