AI engineering glossary · Deep learning core
What is MLP (multilayer perceptron)?
Multilayer perceptron (also called MLP): A feedforward network made of fully connected layers, where every neuron connects to every neuron in the next layer, with non-linear activations in between. With at least one hidden layer it can learn non-linear patterns that a single-layer model cannot.
Multilayer perceptron: an example
An MLP with layers 20 -> 64 -> 32 -> 1 can predict a customer's monthly spend from 20 features.
Related terms
More Deep learning core terms
- Negative log-likelihood
- Neural network pruning
- Neural tangent kernel
- Neuron
- One-cycle policy
- Optimiser
- Orthogonal initialisation
- Output layer
Where you learn it
Multilayer perceptron is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.