Machine Learning

Bias (Math) or Bias Term

See also: Machine learning terms The bias term is a learnable additive constant b added to the weighted sum of a neuron's inputs before an activation function...

MathematicsNeural Networks

Bias-variance tradeoff

The bias-variance tradeoff is a foundational concept in machine learning and statistics that describes the tension between two competing sources of error in...

Statistics

Bigram

A bigram (also written 2-gram) is a contiguous sequence of two adjacent elements, typically two words or two characters, taken from a body of text or speech....

Natural Language Processing

Binary Classification

See also: Classification model, Multi-class classification Binary classification is a supervised learning task in which a model assigns each input to exactly...

Binary condition

A binary condition is a test at a node of a decision tree that has exactly two possible outcomes, typically yes or no (equivalently true or false), routing an...

Boosting

Boosting is an ensemble learning method in machine learning that trains a sequence of weak learners, each one correcting the errors of its predecessors, and...

Bounding Box

A bounding box is a rectangular region defined by a set of coordinates that encloses an object of interest within an image, video frame, or three-dimensional...

Computer Vision

Broadcasting

Broadcasting is the set of rules that lets element-wise operations (addition, subtraction, multiplication, division) act on arrays or tensors of different but...

Deep LearningMathematics

Bucketing

Bucketing, also called binning or discretization, is a feature engineering technique in machine learning that converts a continuous feature into a small number...

Data & Datasets

Byte-Pair Encoding

Byte-pair encoding (BPE) is a subword tokenization algorithm that splits text into tokens by starting from individual characters or bytes and iteratively...

Large Language ModelsNatural Language Processing

CART algorithm

The CART algorithm (Classification And Regression Trees) is a non-parametric supervised learning method that builds a binary decision tree from labelled...

Algorithms

CIDEr

CIDEr (Consensus-based Image Description Evaluation) is an automatic evaluation metric for image captioning that scores a machine-generated caption by how...

Computer VisionModel Evaluation

CLIP (Contrastive Language-Image Pre-training)

CLIP (Contrastive Language-Image Pre-training) is a multimodal neural network developed by OpenAI that learns visual concepts from natural language by training...

Computer VisionDeep Learning

COCO dataset

COCO (Common Objects in Context) is a large-scale dataset for object detection, image segmentation, keypoint detection, and image captioning. Created by a team...

Computer VisionData & Datasets

CRUXEval

CRUXEval (Code Reasoning, Understanding, and eXecution Evaluation) is a benchmark designed to measure how well large language models can reason about,...

AI BenchmarksAI Code Generation

Calibration (machine learning)

Calibration in machine learning is the property that the probability scores produced by a probabilistic classifier match the empirical frequency of the...

Statistics

Calibration Layer

A calibration layer is a post-prediction adjustment appended to a trained machine learning model that rescales its raw output scores or predicted probabilities...

Deep LearningModel Evaluation

Candidate Generation

Candidate generation is the first stage in a multi-stage recommendation system or information retrieval pipeline. Its purpose is to quickly narrow a large...

Information Retrieval

Candidate Sampling

Candidate sampling is a family of training-time optimization techniques used in machine learning to reduce the computational cost of models that must choose...

Natural Language ProcessingNeural Networks

Candle (HuggingFace Rust ML)

Candle is a minimalist machine learning framework written in pure Rust and published by Hugging Face under the huggingface/candle GitHub repository.[^1] The...

Developer ToolsOpen Source AI

CatBoost

CatBoost is an open-source gradient boosted decision trees library developed by Yandex and released to the public on July 18, 2017 [1][5]. The name is a...

AlgorithmsOpen Source AI

Categorical Data

Categorical data, also called qualitative data, is data whose values are discrete labels or groups (such as colors, country names, or blood types) rather than...

Data & DatasetsStatistics

Causal Language Model

A causal language model (CLM), also called an autoregressive language model or a decoder-only language model, is a language model that predicts the next token...

Deep LearningNatural Language Processing

Causal inference

Causal inference is the field of study concerned with drawing conclusions about cause-and-effect relationships from data, answering questions of the form "what...

Statistics

Causal scrubbing

Causal scrubbing is a methodology in mechanistic interpretability for rigorously and quantitatively testing hypotheses about the internal computational...

AI Safety

Centroid

See also: Machine learning terms A centroid is the geometric center of a set of points, computed as the arithmetic mean of their coordinates: each component of...

Centroid-based clustering

See also: Machine learning terms Centroid-based clustering is a family of machine learning algorithms that group data by representing each cluster with a...

Chain of Thought Monitorability

Chain of thought monitorability is the property that lets safety researchers read a reasoning model's chain-of-thought (CoT), the step-by-step working it...

Deep Learning

Chain-of-Thought

Chain-of-thought (CoT) prompting is a prompt engineering technique that improves the reasoning ability of large language models by having them generate a...

Deep LearningNatural Language Processing

Checkpoint

See also: Machine learning terms In machine learning, a checkpoint is a saved snapshot of a model's state captured at a specific point during the training...

Deep Learning

Chelsea Finn

Chelsea Finn (born October 8, 1992) is an American computer scientist, an assistant professor of computer science and electrical engineering at Stanford...

PeopleRobotics

Chinchilla scaling laws

The Chinchilla scaling laws are a set of empirical findings published by DeepMind researchers in 2022 showing that, for a fixed compute budget, a large...

AI ResearchDeep Learning

Chunked prefill

Chunked prefill is a scheduling technique for large language model serving that splits the processing of a long input prompt (the prefill) into smaller,...

AI Infrastructure

Circuit Breakers (Representation Rerouting)

Circuit Breakers are an AI safety method, introduced in 2024, that aims to make a large language model (LLM) or multimodal model robust to harmful generations...

AI Safety

Class

In machine learning, a class is one of the discrete categories that a classification model can assign to an input. Google's Machine Learning Glossary defines a...

Class-Imbalanced Dataset

A class-imbalanced dataset is a dataset in which the distribution of examples across the target classes is significantly unequal, so that one class (the...

Data & Datasets

Classification (machine learning)

Classification in machine learning is the supervised learning task of training an algorithm to assign discrete category labels to input data, in contrast to...

Classification Threshold

A classification threshold (also called a decision threshold or cut-off point) is a numeric value used to convert the continuous probability output of a...

Model Evaluation

Claude Sonnet 4.5

[](/wiki/fileclaudesonnet45logo1png) Claude Sonnet 4.5 is a multimodal large language model (LLM) developed by Anthropic and released on September 29, 2025,...

AI Code GenerationAI Tools & Products

Cleanlab

Cleanlab is an open source Python library for automatically finding and fixing label errors and other data quality problems in machine learning datasets, and...

AI CompaniesOpen Source AI

Clipping

Clipping is a family of techniques in machine learning that constrain numerical values to lie within a specified range or below a specified magnitude. The most...

Deep LearningTraining & Optimization

Cloud TPU

Cloud TPU is Google Cloud's offering of Tensor Processing Units (TPUs), the family of custom application-specific integrated circuits (ASICs) that Google...

AI HardwareAI Infrastructure

Clustering

See also: Machine learning terms Clustering is an unsupervised learning technique that groups a set of data points into clusters so that points in the same...

Co-Adaptation

Co-adaptation in neural networks refers to a phenomenon in which different hidden units develop highly correlated behavior, becoming excessively dependent on...

Deep LearningNeural Networks

Co-Training

Co-training is a semi-supervised learning algorithm that leverages both labeled and unlabeled data by training two classifiers on two distinct "views" of the...

Coconut (Chain of Continuous Thought)

Coconut (Chain of Continuous Thought) is a reasoning paradigm for large language models introduced by researchers at FAIR at Meta, Meta's Fundamental AI...

AI Agents

CodeContests

CodeContests is a competitive programming dataset created by Google DeepMind for training and evaluating machine learning models on algorithmic problem-solving...

AI BenchmarksAI Code Generation

Collaborative filtering

Collaborative filtering (CF) is a family of techniques used in recommendation systems that predicts a user's preferences by collecting and analyzing preference...

Common Crawl

Common Crawl is a nonprofit 501(c)(3) organization that maintains a free, open repository of web crawl data, and it is the single largest publicly available...

Data & DatasetsNatural Language Processing

Compound AI System

A compound AI system is an AI system that achieves its objectives by combining multiple interacting components, such as large language models, retrieval...

Artificial IntelligenceLarge Language Models

Computer vision

Computer vision is the field of artificial intelligence that enables computers to extract meaning from digital images, video, and 3D data, performing tasks...

Artificial IntelligenceComputer Vision

Computer-use agent

A computer-use agent (CUA) is a category of AI agent in artificial intelligence that performs tasks by directly operating a general-purpose computer's...

AI AgentsArtificial Intelligence

Concept drift

Concept drift is the change over time in the statistical relationship between a model's inputs and its target, formally when the joint distribution P(X, Y)...

Data ScienceMLOps

Condition

In machine learning, a condition is any node in a decision tree that performs a test on one or more features and routes an example to one of its child nodes...

Confident Learning (CL)

Confident Learning (CL) is a data-centric machine learning framework for characterizing, finding, and learning with label errors in datasets. It works by...

Confirmation Bias

Confirmation bias is the tendency to search for, interpret, favor, and recall information in ways that confirm one's preexisting beliefs, and in artificial...

AI EthicsAI Safety

Confusion Matrix

A confusion matrix is a table that summarizes the performance of a classification model by tabulating its predicted class labels against the actual class...

Model Evaluation

Context window

A context window (also called context length) is the maximum number of tokens that a large language model (LLM) can process at once, spanning both the input...

Artificial IntelligenceDeep Learning

Continual learning

Continual learning, also called lifelong learning or incremental learning, is a machine learning paradigm in which a model learns from a stream of tasks or...

Deep LearningNeural Networks

Continuous Feature

A continuous feature is a numeric input variable in machine learning and statistics that can take any value within a range, including decimals and fractions,...

Data & DatasetsStatistics