Neural Networks

Feed Forward

Data flows in one direction, input to output, with no loops.

The plainest architecture: fully connected layers stacked in sequence, each one transforming the previous layer output. Also called a multilayer perceptron.

It remains the right default for tabular data and lives inside larger architectures as the position-wise block in every transformer.

Also in Neural Networks

Perceptron Backpropagation Hopfield Network Boltzmann Machine Self Organising Maps Deep Belief Network

JOIN NOW

Begin the first module

It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.

See the curriculum

Join any time · Build AI skills at your pace