Research history Concepts

An artificial neural network is a computing system of many simple connected units whose behaviour is set by connection weights. Its roots lie in 1943 models of neurons, and its learning versions began with Frank Rosenblatt's perceptron in 1958.

A framework that treats information as a measurable quantity to be encoded and transmitted, founded in Shannon's 1948 paper; it gave the field the bit, entropy and channel capacity.

The Turing test is Alan Turing's 1950 proposal for replacing the question "Can machines think?" with a game: a machine passes if an interrogator cannot tell its written answers apart from a human's.

AI winter is a period of sharply reduced funding and interest in artificial intelligence research. The field's hype cycles have produced two such downturns, usually dated to about 1974–1980 and 1987–2000.

A recurrent neural network introduced by John Hopfield in 1982 that stores patterns as minima of an energy function and recalls them from partial or distorted input, bringing statistical mechanics into the study of neural networks.

Autonomous driving is the operation of a road vehicle by a computer system instead of a person. Its six automation levels, its two main technical traditions and its long line of research vehicles define how the field is discussed today.

Backpropagation is the procedure that lets a multilayer neural network learn by sending output errors backward to adjust its weights, using gradient descent. A 1986 Nature paper made it widely known, and it is standard in most neural networks today.

Imitation learning trains an agent by supervised learning on expert demonstrations rather than by trial and error. Its simplest form is behaviour cloning, and its best-known weakness is distribution shift.

A convolutional neural network applies the same small pattern detectors across a whole image, so a feature is found wherever it appears. Trained with backpropagation in 1989 and refined as LeNet-5 in 1998, it became standard in computer vision.

Attention scores how important each element of a sequence is relative to the others and turns those scores into weights, letting a model read any part of its input directly. It is the operation at the core of the transformer.

A generative adversarial network pits a generator that makes fake data against a discriminator that judges it, both trained in a zero-sum game; proposed by Ian Goodfellow and colleagues in 2014, it led to a series of architectures for generating images.

A residual connection adds a block's input to its output, so the block learns only the change it needs to make. This makes very deep networks trainable, and it is a standard part of today's transformers.

Alignment is the problem of making a model's behaviour match what its users and designers actually intend, not just what its training objective literally rewards. Training on human preference comparisons is one practical route to it.

Reinforcement learning is the branch of machine learning and optimal control in which an agent learns, by trial and error, which actions in a dynamic environment maximise a reward signal.

Supervised learning trains a model to map inputs to outputs using paired labelled examples, so that it can predict answers for new, unseen data. Its central measure of success is how well the model generalises beyond the training set.

Unsupervised learning trains algorithms on data that carry no labels, letting them find structure such as clusters, low-dimensional representations or generative models. It underlies clustering tools and neural generative models from the Hopfield network and Boltzmann machine to the variational autoencoder.

AGI is the goal of AI systems that match or beat humans across a broad range of tasks. The term has no agreed definition; a framework by Morris et al. grades systems by performance level and generality.

A vision-language-action model (VLA) is a robot policy that takes in camera images and a language instruction and outputs actions directly, usually by adapting a pretrained vision-language model to control.

Hallucination is false or misleading information that a model presents as fact. It is a central failure mode of text-generating systems and a main obstacle to trusting their output.

A supervised maximum-margin model for classification and regression that separates classes by the widest possible margin and uses kernel functions to handle non-linear data.

A Boltzmann machine is a neural network whose configurations are scored by a global energy and trained by a stochastic learning algorithm. Introduced by Geoffrey Hinton and Terry Sejnowski, it brought energy-based models into cognitive science and machine learning.

A recurrent neural network (RNN) is a neural network with feedback connections that carry information from one step of a sequence to the next. Its long short-term memory variant (LSTM) was designed to keep useful memories over longer spans.

AdaBoost, short for Adaptive Boosting, is a statistical classification meta-algorithm introduced by Yoav Freund and Robert Schapire in 1995. It reweights training examples, trains weak classifiers in sequence and combines their outputs into one weighted classifier.

Topic models represent documents as mixtures of latent topics, giving a compact statistical description of text collections. The 2003 Latent Dirichlet Allocation paper formalized this idea as a hierarchical Bayesian model.

A word embedding represents each word as a list of numbers learned from text, so that words used in similar ways get similar lists. Embeddings are a basic building block of modern language models.

Connectionist temporal classification (CTC) is a method for training recurrent neural networks to label unsegmented sequences, such as speech or handwriting, without frame-by-frame alignment. Introduced in 2006, it let CTC-trained LSTMs win the first international contests for recurrent networks.

Deep neural network acoustic modeling uses multilayer networks to map speech to units such as phones. A 2010 NIPS paper used Deep Belief Nets and a mean-covariance RBM to extract speech features, reaching 20.5% phone error on TIMIT.

Graphics processing units (GPUs) run many arithmetic operations in parallel, which suits neural-network training. Their use from 2010 onward made deep learning practical at much larger scales.

Xavier (Glorot) initialization is a weight-initialization scheme from Glorot and Bengio's 2010 paper that sets each layer's starting weight scale so signals stay stable across layers, giving substantially faster convergence in deep feedforward networks.

A variational autoencoder is a generative model whose encoder maps an input to a distribution over a latent space and whose decoder reconstructs the input from a sample; training maximises a lower bound on the data likelihood.

A technique that re-centres each layer's inputs to zero and rescales them to unit variance over a mini-batch, making deep networks faster and more stable to train.

Deepfake is synthetic media: images, video or audio made or altered with AI. The term, a blend of "deep learning" and "fake", appeared in late 2017 and now names a whole class of face-swapping and manipulation techniques.

Model parallelism splits one model's parameters and computation across multiple accelerators, so networks too large for a single device can still be trained. NVIDIA's 2019 Megatron-LM paper showed an intra-layer version built in native PyTorch.

A state space model represents a sequence as a hidden state that evolves with the input. S4 brought the idea into deep learning in 2021, and Mamba made its parameters input-dependent, enabling linear-time modeling of long sequences.

A loss function turns the cost of a prediction into a single number, and training a model means making that number as small as possible. Its choice decides which mistakes a model is punished for.

Overfitting is when a model fits its training data so closely that it performs poorly on new data. It is one half of the bias–variance trade-off and is usually spotted by comparing training and validation performance.

Regularization is the practice of making a problem's answer simpler, usually by adding a penalty term to the objective, so that ill-posed problems become solvable and models avoid overfitting.

A function applied to each node's weighted sum, giving neural networks their non-linearity. Sigmoid, tanh and ReLU shaped early deep learning; GELU now dominates transformers.

Embodied AI is the study of agents that learn by interacting with an environment, using egocentric perception, rather than only from datasets curated from the internet. Simulators serve as virtual testbeds where such agents are trained and evaluated.

Benchmark contamination means the test items a model is evaluated on, or close variants of them, were present in its pretraining data, so scores partly measure memory of seen text rather than the ability the benchmark is meant to probe.

Mechanistic interpretability explains model behaviour by finding the internal computations and features that produce it. Work on superposition and sparse autoencoders shows how many features can be packed into few neurons.

Reward hacking is what happens when a system optimises a proxy reward that only imperfectly captures what we want: it scores well on the proxy while performing badly on the true objective.

The Semantic Web is a W3C standards effort that uses RDF and OWL to describe data so different applications, enterprises and communities can share and reuse information, moving from research toward practical tools.

Visual odometry lets a rover measure how far it actually moved by tracking features in camera images taken before and after a short drive, instead of trusting wheel turns. NASA's Mars Exploration Rovers were the first to demonstrate it.

k-means clustering splits n observations into k groups by repeatedly sending each point to its nearest centroid and recomputing each centroid as its cluster's mean. It is simple and scales to large data, but k must be fixed in advance.

A model validation technique that repeatedly splits data into folds, trains on some parts and validates on others, then averages the results to estimate how well a model or statistical result will generalise to unseen data.

Graph neural networks are neural networks built for graph-structured data, in which nodes repeatedly exchange messages with their neighbours. Since the model was formulated in 2009, they have become a standard way of learning on graphs.

A regularisation technique for neural networks: during training it randomly zeroes the inputs or outputs of some neurons so that units cannot co-adapt, which reduces overfitting.

Decision tree learning builds a classification or regression tree from data by repeatedly splitting it into more homogeneous groups. It is a widely used supervised method whose rules can be read directly, and whose main weaknesses are instability and a tendency to overfit.

An autoencoder is an unsupervised neural network that compresses its input into a low-dimensional code and reconstructs it back, learning a latent representation useful for dimensionality reduction, denoising and anomaly detection.