Skip to content
Category

Deep learning

page 1
deep learning
branch of machine learning
large language model
language model built with very large amounts of texts
generative artificial intelligence
artificial intelligence model capable of generating content in response to a prompt
Google DeepMind
artificial intelligence company owned by Google
prompt engineering
creation or optimization of a prompt to be given to an artificial intelligence model
hallucination
confident unjustified claim by an AI
long short-term memory
artificial recurrent neural network architecture used in deep learning
AI accelerator
device that provides hardware acceleration for artificial intelligence applications
question answering
research area in computer science
fine-tuning
process of taking a pre-trained model and further training it on a smaller, specific dataset to adapt or improve its performance for a particular task or domain
foundation model
artificial intelligence model paradigm
stochastic parrot
metaphor to describe the theory that large language models, though able to generate plausible language, do not understand the meaning of the language they process
knowledge distillation
machine learning method to transfer knowledge from a large model to a smaller one
residual neural network
type of artificial neural network
dropout
regularization method for artificial neural networks
deep reinforcement learning
techniques combining deep learning and reinforcement learning principles to create efficient machine learning algorithms
Google Wavenet
WaveNet is a deep neural network for generating raw audio. It was created by researchers at London-based AI firm DeepMind. The technique, outlined in a paper in September 2016, is able to generate relatively realistic-sounding human-like voices by directly modelling waveforms using a neural network method trained with recordings of real speech. Tests with US English and Mandarin reportedly showed that the system outperforms Google's best existing text-to-speech (TTS) systems, although as of 2016 its text-to-speech synthesis still was less convincing than actual human speech. WaveNet's ability
physics-informed neural networks
innovative technique to solve partial differential equations
hierarchical temporal memory
biological theory of intelligence
hyperdimensional computing
approach to artificial intelligence that represents information as vectors of up to thousands of components
EleutherAI
EleutherAI () is a non-profit artificial intelligence (AI) research group. The group, considered an open-source version of OpenAI, was formed in a Discord server in 2020 to create an open-source version of GPT-3. In early 2023, it formally incorporated as the EleutherAI Institute, a non-profit research institute. As of 2025, the nonprofit maintains widely-used training datasets, conducts research, and is involved in public policy, among other activities.
Neural scaling law
Law in machine learning
Multi-agent reinforcement learning
sub-field of reinforcement learning
Neural network Gaussian process
modeling tool for assigning probabilities to events
Digital cloning
Artificial intelligence technology