Knowledge Graph — Coursera Notes › Academic disciplines › Computer Science / Information Technology › Artificial Intelligence › Neural Network

Feedforward Neural Network (FNN)

concept · part of Neural Network

A neural network where data flows in one direction from input to output, used for classification and regression tasks. It is the simplest type of neural network without feedback loops, employing activation functions like ReLU and Sigmoid, and is trained via backpropagation.

FNNs are ideal for tasks with clear input-output mapping like regression and classification, e.g., predicting housing prices from features like bedrooms and square footage.

Inside Feedforward Neural Network (FNN) (1)

• Activation function — Activation functions introduce non-linearity into neural networks.

This is the text view of an interactive 3D knowledge graph — open this page with JavaScript enabled to explore it visually.