Machine Learning

Machine learning terms/Decision Forests

See also: Machine learning terms Decision forests are a family of machine learning models built from collections of decision trees. Instead of relying on a...

Machine learning terms/Fairness

The key machine learning fairness terms are the formal criteria used to define and measure when a model treats demographic groups equitably, together with the...

AI EthicsArtificial Intelligence

Machine learning terms/Fundamentals

See also: Machine learning terms Machine learning (ML) is the branch of artificial intelligence concerned with building systems that learn patterns from data...

Machine learning terms/Google Cloud

Google Cloud is the public cloud arm of Google and one of the three dominant providers of machine learning infrastructure, alongside Amazon Web Services and...

AI InfrastructureGoogle

Machine learning terms/Natural Language Processing

Natural Language Processing (NLP) is the subfield of artificial intelligence and machine learning concerned with enabling computers to read, interpret,...

Large Language ModelsNatural Language Processing

Machine learning terms/Recommendation Systems

See also: Machine learning terms A recommendation system (also called a recommender system) is a class of machine learning software that predicts the...

Machine learning terms/Reinforcement Learning

See also: Machine learning terms Reinforcement learning (RL) is a branch of machine learning in which an agent learns to make sequential decisions by...

Reinforcement Learning

Machine learning terms/Sequence Models

See also: Machine learning terms Sequence models are a class of machine learning systems designed to process inputs or produce outputs that have a meaningful...

Model Architecture

Machine learning terms/TensorFlow

See also: Machine learning terms TensorFlow is an open-source software library for machine learning, deep learning, and numerical computation, developed and...

Deep Learning

Machine translation

Machine translation (MT) is the use of software to automatically translate text or speech from one natural language to another without human intervention. As...

Artificial IntelligenceNatural Language Processing

Majority class

In machine learning, the majority class is the class label that appears most frequently in a labeled dataset used for classification. It is the direct...

Manifold Learning

Manifold learning is a class of nonlinear dimensionality reduction techniques in machine learning and statistics that recover a low-dimensional structure...

Margaret Mitchell (computer scientist)

Margaret Mitchell is an American computer scientist who works on AI ethics, fairness in machine learning, and the documentation of AI systems. She is best...

AI EthicsPeople

Markov Decision Process (MDP)

See also: Machine learning terms A Markov Decision Process (MDP) is a mathematical framework for modeling sequential decision-making in stochastic...

MathematicsReinforcement Learning

Masked Language Model

A masked language model (MLM) is a language model trained to predict missing tokens that have been hidden in a sequence of text, using context from both the...

Deep LearningNatural Language Processing

Masked autoencoder (MAE)

Masked autoencoder (MAE) is a self-supervised learning method for vision transformers that masks roughly 75% of an input image's patches and trains a network...

Computer VisionTraining & Optimization

Matplotlib

Matplotlib is the foundational open-source data visualization library for Python, created by John D. Hunter in 2003, that produces static, animated, and...

AI Tools & ProductsData Science

Matrix factorization

Matrix factorization is a family of mathematical techniques that decompose a matrix into a product of two or more smaller matrices. Originally rooted in linear...

Mathematics

Matryoshka representation learning

Matryoshka Representation Learning (MRL) is a representation learning technique that trains a single neural model to produce embedding vectors which remain...

Information RetrievalNatural Language Processing

Maximum likelihood estimation (MLE)

Maximum likelihood estimation (MLE) is the method of choosing the parameters of a probability model so that they make the observed data as probable as...

Statistics

Mean Absolute Error (MAE)

Mean Absolute Error (MAE) is a regression accuracy metric and loss function that measures the average absolute difference between predicted values and actual...

Model EvaluationStatistics

Mean Squared Error (MSE)

See also: Machine learning terms Mean Squared Error (MSE), also called mean squared deviation (MSD), is the average of the squared differences between...

Model EvaluationStatistics

MemGPT

MemGPT (short for Memory-GPT) is a system and agent design pattern that gives large language model agents long-term memory by managing data between the model's...

AI Agents

Membership Inference Attack

A Membership Inference Attack (MIA) is a privacy attack against a trained machine learning model in which an adversary, given a candidate data record and...

AI Safety

Meta Prompting

Meta prompting (also spelled meta-prompting) is an advanced prompt engineering technique where large language models (LLMs) are used to generate, refine,...

Artificial IntelligenceNatural Language Processing

Meta-Learning

See also: Machine learning terms, Few-shot learning, Transfer learning Meta-learning, often called "learning to learn", is a branch of machine learning in...

Deep Learning

Metric

In machine learning, a metric is a quantitative measure used to evaluate how well a model or algorithm performs a task. Google's Machine Learning Glossary...

Metrics API (tf.metrics)

See also: Machine learning terms The Metrics API in TensorFlow is a collection of classes and utilities for computing evaluation scores that summarize how well...

Microscaling formats

Microscaling (MX) formats are a family of low-precision number formats for machine learning in which a small block of values, normally 32 of them, shares one...

AI HardwareAI Infrastructure

Mini-batch

A mini-batch is a small, randomly sampled subset of the training dataset used to compute a single update to a model's parameters during training. In machine...

Minimax Loss

Minimax loss is a loss function rooted in game theory and decision theory that measures the worst-case performance of a strategy, algorithm, or model. In...

Generative AIMathematics

Minority class

In an imbalanced classification problem, the minority class is the class label with far fewer training examples than the others, and it is almost always the...

Mixed-Precision Training

Mixed-precision training is a technique for training deep learning models using lower-precision floating-point formats for most computations while maintaining...

Deep Learning

Mixture of Agents

Mixture of Agents (MoA) is a multi-model collaboration framework that combines multiple large language models (LLMs) in a layered architecture, where models in...

AI AgentsArtificial Intelligence

Mixture of Depths

Mixture of Depths (MoD) is a technique for dynamically allocating computation to individual tokens within transformer-based language models. Introduced by...

Deep LearningModel Architecture

Mixture of Experts (MoE)

A Mixture of Experts (MoE) is a machine learning architecture that divides a problem into subtasks, each handled by a specialized sub-network called an...

Deep LearningNeural Networks

Modality

A modality in machine learning and artificial intelligence is a distinct type, form, or structure of data that a model can process, learn from, or generate....

Deep Learning

Model

In machine learning, a model is a mathematical representation of a real-world process that learns patterns from data and uses those patterns to make...

Model Capacity

Model capacity is the size and richness of the family of functions a machine learning model can represent and learn, which determines how complex a pattern the...

Model Evaluation

Model Evaluation

Model evaluation is the process of measuring how well a machine learning model performs on data it was not trained on, in order to estimate how it will...

Model Parallelism

See also: Machine learning terms, Data parallelism, GPU computing, Deep learning Model parallelism is a distributed training and inference technique that...

AI InfrastructureDeep Learning

Model collapse

Model collapse is a degenerative process in which generative AI models trained recursively on data produced by previous-generation models progressively lose...

AI Safety

Model extraction attack

A model extraction attack is a class of machine learning security attacks in which an adversary, restricted to black-box query access to a target model...

AI Safety

Model merging

Model merging combines the parameters of multiple trained neural networks into a single unified model without any additional training. Rather than running...

Deep LearningLarge Language Models

Model soups

Model soups is a weight-averaging technique (a form of model merging) that combines several independently fine-tuned neural networks into a single model by...

Reinforcement Learning

Model stealing

Model stealing (also known as model extraction, model functionality extraction, or model theft) is an adversarial machine learning attack in which an adversary...

AI Safety

Model training

Model training is the process of fitting a machine learning model's parameters to data so that it makes accurate predictions on new, unseen inputs. The...

ModelScope

ModelScope is an open-source Model-as-a-Service (MaaS) platform developed by Alibaba Cloud and DAMO Academy and launched on November 3, 2022, that functions as...

Chinese AIDeveloper Tools

Multi-Class Classification

Multi-class classification is a supervised learning task in machine learning that assigns each input to exactly one of three or more mutually exclusive...

Multi-Class Logistic Regression

See also: Machine learning terms, Logistic regression, Classification Multi-class logistic regression, also known as multinomial logistic regression, softmax...

Statistics

Multi-Head Self-Attention

Multi-head self-attention is the core sequence-mixing mechanism of the Transformer architecture: it runs several scaled dot-product attention operations...

Deep LearningModel Architecture

Multi-head Latent Attention

Multi-head Latent Attention (MLA) is an attention mechanism for transformer models that achieves a 93.3% reduction in key-value cache size while maintaining or...

Deep LearningModel Architecture

Multi-token prediction

Multi-token prediction (often abbreviated MTP) is a language modeling training objective in which the model is trained to predict several future tokens at each...

Large Language ModelsTraining & Optimization

Multimodal Model

A multimodal model is an artificial intelligence system that processes, relates, and generates information across two or more types of data, or modalities,...

Computer VisionDeep Learning

Multinomial classification

See also: Machine learning terms Multinomial classification, also called multiclass or multi-class classification, is the supervised learning task of assigning...

Multinomial regression

See also: Machine learning terms Multinomial regression is a statistical model that predicts which one of K possible categories an observation belongs to,...

N-gram

An n-gram is a contiguous sequence of n items extracted from a given sample of text or speech, where the items can be characters, syllables, words, or other...

Natural Language Processing

NVFP4

NVFP4 (NVIDIA FP4) is a 4-bit floating-point number format introduced by Nvidia with the Blackwell GPU architecture. It stores each value in just 4 bits using...

AI HardwareNVIDIA

NaN Trap

See also: gradient descent, backpropagation, loss function, mixed precision training, numerical stability A NaN trap (short for "Not a Number" trap) is a...

Deep LearningTraining & Optimization

Naive Bayes

Naive Bayes is a family of probabilistic classification algorithms that apply Bayes' theorem under a strong ("naive") assumption that every feature is...

Statistics