What Is a Learning Model?
Every page in this section describes a different way of answering the same question: given some examples, how should a system change itself so that it handles the next one correctly? The honest answer is never "it…
How Machines Learn
What different learning systems retain from experience and how that retained structure produces a decision -- perceptrons, RAM networks, RBF networks, SOMs, SVMs, and more, explored through one shared dataset.
What Is an Artificial Neuron?
The name invites a comparison the mechanism doesn't really support. An artificial neuron is a small, specific arithmetic operation — multiply each input by a learned number, add them up, add one more learned number…
The Perceptron and Linear Classification
Rosenblatt's perceptron, from 1958, is the first complete learning algorithm this section covers: a single artificial neuron with a threshold activation, plus a rule for adjusting its weights automatically from labelled…
How Weighted Neural Networks Learn
A hidden layer fixes what a single perceptron can represent, but it opens a new problem: the only thing directly observable during training is the error at the very end, at the output layer, yet every weight in every…
Feedforward Networks and Multilayer Perceptrons
Stack artificial neurons into layers — an input layer, one or more hidden layers, an output layer — with every unit in one layer feeding every unit in the next, and no connection ever running backward during inference…
Weightless Neural Networks and RAM Networks
Every model so far in this section stores what it's learned as numerical weights. RAM networks — also called weightless neural networks, or N-tuple recognisers — store it a completely different way: as values written…
Radial Basis Function Networks
Every hidden unit in a Radial Basis Function (RBF) network asks the same simple question about a new input: how close is it to one particular remembered point? That remembered point is the unit's centre , and "how…
Self-Organising Maps
Every model up to this page has been supervised — trained against known labels. A Self-Organising Map (SOM), introduced by Kohonen in 1982, is this section's first genuinely unsupervised architecture: it is handed…
Recurrent Neural Networks
Every architecture so far treats each input as a single, self-contained snapshot. A sentence, an audio clip, a stock price history — these have sequential structure, where the right answer at one position usually…
Associative-Memory and Hopfield Networks
A Hopfield network, introduced by Hopfield in 1982, answers a different question than every other architecture in this section 1 : not "what label does this input get," but "given a noisy or partial version of something…
Support Vector Machines
A Support Vector Machine (SVM) is a supervised, maximum-margin classifier — not, despite sharing this section with so many architectures that are, an artificial neural network at all. It belongs here for the same reason…
Nearest-Neighbour and Instance-Based Learning
Every model in this section so far distils the training data into something smaller than the data itself — weights, a tree, a set of support vectors, a grid of prototypes. A k-nearest-neighbour (k-NN) classifier…
Convolutional Neural Networks
A fully-connected layer treats every pixel of an image as an independent input, with its own separate weight to every hidden unit — which throws away the one fact that actually matters about images: a pattern worth…
Autoencoders
An autoencoder is trained to do something that sounds pointless stated plainly: reproduce its own input as its output. The point isn't the reconstruction itself — it's what the network is forced to learn in order to do…
Attention and Transformers
This page assumes the RNN page 's own starting question — what if the right output depends on earlier elements of a sequence — and picks up exactly where that page's own limitation left off: a plain recurrent network…
Decision Trees and Ensembles
Every model so far in this section fits one global equation, or one distance measure, or one grid — some single structure applied the same way to every input. A decision tree does something categorically different: it…
Neural Networks and Alternative Models
Laid out as a single historical line — perceptron, then MLP, then the rest — this section's architectures would look like one lineage of fixes. They aren't. Weighted networks, RAM networks, prototype-based networks…