Concepts
Multilayer perceptron
1 · In one line
A multilayer perceptron can fit a nonlinear model to training data.
1 · What it is
Nonlinear activations create complex mappings between model inputs and outputs. A dense layer computes an activation from an input-kernel dot product and a bias.
Hidden units can come to represent task features during training. A multiclass output can use softmax to return one probability per class.
Gradients are calculated using backpropagation. Large feedforward networks can overfit small training sets. Scikit-learn’s MLPClassifier supports only cross-entropy loss.
Nonlinear activations create complex mappings between inputs and outputs.
Nonlinear patternsAn MLP can fit a nonlinear model to training data.
Learned featuresHidden units can come to represent task features during training.
Many outputsA multiclass output can use softmax to return one probability per class.
Follow three features through a one-hidden-layer MLP.
- 1 · receiveRead the input data.
- 2 · projectCompute an input-kernel dot product and add a bias.
- 3 · activateApply a nonlinear activation to the hidden values.
- 4 · outputApply softmax as the multiclass output function.
- 5 · learnBackpropagate the output error and adjust the connection weights.
Nonlinear activations create complex mappings between model inputs and outputs.
| Who | What they ask | What it works with |
|---|---|---|
| Risk team | “Which class matches this tabular record?” | Numeric and encoded categorical features |
| Forecasting team | “What numeric value follows from these measurements?” | A fixed-length feature vector |
| Research team | “Does a nonlinear baseline improve on a linear classifier?” | Labelled training examples |
solves
- An MLP can fit a nonlinear model to training data.
- Gradients are calculated using backpropagation.
- MLPClassifier applies softmax as its multiclass output function.
doesn't solve
- Large feedforward networks can overfit small training sets.
- Scikit-learn's MLPClassifier supports only cross-entropy loss.
6 · Go deeper
Sources used
This explainer is written in original language. The links below support its factual claims.
- docsNeural network models (supervised), scikit-learn · read 28 Sept 2026
- docsMLPClassifier, scikit-learn · read 28 Sept 2026
- docsDense layer, Keras · read 28 Sept 2026
- docsBuild the Neural Network, PyTorch · read 28 Sept 2026
- paperLearning representations by back-propagating errors, Rumelhart, Hinton and Williams, Nature · read 28 Sept 2026
- paperImproving neural networks by preventing co-adaptation of feature detectors, Hinton et al. · read 28 Sept 2026