Machine Learning Fundamentals · Neural networks

Neural network basics

Stacking layers of logistic-regression-like units, connected by non-linear activation functions, to learn more complex patterns.

Also known as: perceptron, activation function, hidden layer.

Start a lesson on Neural network basics

Learn first

• Logistic regression: A linear model adapted for classification by squashing its output into a probability.
• Gradient descent: Repeatedly nudging a model's parameters downhill on the cost function to reduce error.

Leads to

• Backpropagation: The algorithm that computes how much each weight in a neural network contributed to the error, so gradient descent knows which way to adjust it.

Related topics

• Backpropagation: The algorithm that computes how much each weight in a neural network contributed to the error, so gradient descent knows which way to adjust it.