Training—Learning Through Gradient Descent

Learn how gradient descent is developed as an advanced learning algorithm that trains a multilayer perceptron model.

Training a neural network

The central question of this lesson is: When we go from a single neuron (perceptron) to a multilayer neural network, would the training algorithm that we used for the perceptron also need to change?

Press + to interact

Let’s take stock of the situation

It’s always a good idea to take a step back and take stock of the things we know. Things that we know will still not change when we complicate the model from a perceptron to a neural network:

  • A neural network still has the same two inputs: acting (0-10) and direction (0-10).

  • It still has one output (Good movie = 1, Bad movie = 0).

  • Each neuron in the neural network is still performing the same operation as that performed by the single neuron in a perceptron: WXW \cdot X ...

Get hands-on with 1400+ tech skills courses.