Information technology

Transfer learning

Batch normalization

Dropout

Batch size

Hyperparameter tuning

Data augmentation

Skip connection

ResNet

LeNet‑5

Vision transformer

T5

GPT

BERT

Multi‑head attention

Attention mechanism

Transformer

Discriminator

Generator

Generative adversarial network

Gated Recurrent Unit

Long Short‑Term Memory

Vanishing gradient

AdaGrad

RMSProp

Adam

Recurrent neural network

Feedforward neural network

ELU

Leaky ReLU

ReLU

Activation function

Bias

Weight

GPU‑accelerated computing

AlexNet

Convolutional neural network

Greedy layer‑wise pre‑training

Multi‑layer perceptron

Moore's Law

Boltzmann machine

parallel logic programming

Fifth Generation Computer Systems project

expert system

perceptron

Speech Understanding Research program

DIPMETER

XSEL

VAX minicomputer

DEC PDP-10

mixed-initiative control strategy