0PricingLogin▼
Learn AI with Python · Lesson

Activation Functions

Sigmoid, ReLU, and Softmax explained.

1

Activation Functions

Activation functions are a critical part of neural networks. They determine whether a neuron should be activated based on the input it receives.

Without activation functions, the neural network would behave as a linear model, limiting its ability to learn complex patterns.

Activation Functions — illustration 1

2

Types of Activation Functions

Common types of activation functions include:

  • Sigmoid: Outputs values between 0 and 1.
  • ReLU (Rectified Linear Unit): Outputs the input if it's positive, otherwise 0.
  • Softmax: Converts outputs into probabilities for classification tasks.

All lessons in this course

  1. Introduction to Neural Networks
  2. Activation Functions
  3. Feedforward Neural Networks
  4. Backpropagation Algorithm
  5. First Neural Network with TensorFlow
← Back to Learn AI with Python