Models Glossary
Browse 310 models terms defined in plain English, from the cultural dictionary of computing.
310 Models Terms
- AI Language
- Language used in AI contexts, either referring to natural language processed by AI systems or to specialized representations, prompts, and conventions used...
- AI Model
- A trained computational model that produces predictions, classifications, generations, or other outputs from input data. In product discussions, AI model may...
- AI Model Registry
- A model architecture concept tied to ai model registry and how modern AI systems represent or process information. It influences how models are trained,...
- AI Parameter
- A configurable value in an AI system, or in some contexts an individual learned weight inside a model. In product discussions, the phrase often refers to...
- AI Training
- The process of adjusting a model's parameters using data so it learns patterns or capabilities relevant to a task or domain. In product discussions, the term...
- Anthropic
- An AI company known for developing large language models and safety-focused techniques, including the Claude family of models. In technical discussions, the...
- Attention Score
- A model architecture concept tied to attention score and how modern AI systems represent or process information. It influences how models are trained,...
- Bidirectional Encoder
- A model architecture concept tied to bidirectional encoder and how modern AI systems represent or process information. It influences how models are trained,...
- Classifier
- A model or component that assigns an input to one or more categories based on learned patterns or defined criteria. Classifiers are widely used in spam...
- Claude
- A family of AI assistant models developed by Anthropic and used for tasks such as conversation, writing, coding, and analysis. In product and engineering...
- Consistency Model
- A model architecture concept tied to consistency model and how modern AI systems represent or process information. It influences how models are trained,...
- Context Extension
- An approach for increasing the amount of context a model can handle, whether through architectural changes, fine-tuning methods, retrieval, or system-level...
- Convolutional Neural Network
- A model architecture concept tied to convolutional neural network and how modern AI systems represent or process information. It influences how models are...
- Data Mixture
- The composition and relative proportions of different datasets or data sources used to train a model. The data mixture can strongly influence what capabilities...
- Decoder
- A model architecture concept tied to decoder and how modern AI systems represent or process information. It influences how models are trained, evaluated, or...
- Dense Layer
- A model architecture concept tied to dense layer and how modern AI systems represent or process information. It influences how models are trained, evaluated,...
- Dense Model
- A model in which most or all parameters are active for each forward pass, unlike sparse architectures such as mixture-of-experts where only subsets activate....
- Encoder
- A model architecture concept tied to encoder and how modern AI systems represent or process information. It influences how models are trained, evaluated, or...
- Encoder-Decoder
- A model architecture concept tied to encoder-decoder and how modern AI systems represent or process information. It influences how models are trained,...
- Feed-Forward Network
- A model architecture concept tied to feed-forward network and how modern AI systems represent or process information. It influences how models are trained,...
- Foundation Model API
- An API that exposes a large general-purpose model for downstream tasks such as chat, generation, embeddings, or tool use.
- Frontier Model
- A model that is near the leading edge of capability for its class at a given point in time. The phrase is often used to describe large general-purpose models...
- Frozen Layer
- A model architecture concept tied to frozen layer and how modern AI systems represent or process information. It influences how models are trained, evaluated,...
- Generative Adversarial Network
- A model architecture concept tied to generative adversarial network and how modern AI systems represent or process information. It influences how models are...
- Generative Model
- A model architecture concept tied to generative model and how modern AI systems represent or process information. It influences how models are trained,...
- Hidden Layer
- A model architecture concept tied to hidden layer and how modern AI systems represent or process information. It influences how models are trained, evaluated,...
- Hugging Face
- An open AI platform and ecosystem known for hosting models, datasets, and NLP tooling. It influences how models are trained, evaluated, or served, and it can...
- Internal Representation
- The hidden encoded form in which a model stores and transforms information while processing inputs. Internal representations are a major focus of...
- Language Model
- A model architecture concept tied to language model and how modern AI systems represent or process information. It influences how models are trained,...
- Language Model Evaluation
- A model architecture concept tied to language model evaluation and how modern AI systems represent or process information. It influences how models are...
- Large Context Model
- A model designed to handle especially large context windows, allowing it to process longer documents, histories, or combined evidence in a single request....
- Lemmatization
- Lemmatization is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Likelihood
- A probabilistic measure of how well a model assigns probability to observed data or candidate outputs. In AI and machine learning, likelihood is central to...
- Linear Layer
- Linear Layer is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Linear Probe
- Linear Probe is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Linear Regression
- Linear Regression is a supervised learning method for estimating numeric outputs from input features. It is commonly used for prediction pipelines and baseline...
- Llama
- Llama is an open-weight family of large language models from Meta. It is commonly used for self-hosted chat, summarization, and fine-tuned assistants, where...
- Logistic Regression
- Logistic Regression is a supervised learning method for estimating numeric outputs from input features. It is commonly used for prediction pipelines and...
- Logit
- Logit is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Long Short-Term Memory
- Long Short-Term Memory is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- LoRA Detail
- LoRA Detail is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- LSTM
- LSTM is a recurrent neural network architecture with gated memory cells. It is commonly used for sequence modeling where long-range dependencies matter, where...
- MAE
- MAE is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Manifold Learning
- Manifold Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Markov Chain
- Markov Chain is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Markov Chain Monte Carlo
- Markov Chain Monte Carlo is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production...
- Maximum Likelihood Estimation
- Maximum Likelihood Estimation is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production...
- Mean Absolute Error
- Mean Absolute Error is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- Mean Squared Error
- Mean Squared Error is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Mechanistic Interpretability
- Mechanistic Interpretability is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production...
- Memorization
- Memorization is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Memory Augmented Network
- Memory Augmented Network is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building...
- Meta-Learning
- Meta-Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Mini-Batch
- Mini-Batch is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Mistral
- Mistral is a family of open and commercial language models from Mistral AI. It is commonly used for instruction following, coding, and efficient serving, where...
- Mixed Precision Training
- Mixed Precision Training is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for...
- MLflow
- MLflow is an MLOps platform for experiment tracking, model packaging, and lifecycle management. It is commonly used for recording runs, registering models, and...
- Model Alignment
- The extent to which a model's behavior matches intended goals, human values, policy constraints, or task requirements. Model alignment is a broad concern...
- Model Architecture
- Model Architecture is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model Benchmark
- A benchmark used to compare models on one or more tasks, capabilities, or operational metrics. Model benchmarks help guide selection, but they should be...
- Model Card Detail
- Model Card Detail is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model Compression
- Model Compression is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model Config
- The configuration associated with a model deployment or usage pattern, including model version, decoding settings, context limits, adapters, and operational...
- Model Context
- The information available to a model at inference time, including the prompt, conversation history, retrieved documents, tool outputs, and other supplied...
- Model Cost
- The cost associated with training, hosting, or running a model in production, including compute, storage, licensing, and operational overhead. Model cost...
- Model Deployment
- The process and resulting setup for releasing a model into an environment where it can serve real workloads. Model deployment includes packaging, routing,...
- Model Distillation
- Model Distillation is a training approach where a smaller student model learns from a larger teacher model. It is commonly used for compressing models while...
- Model Editor
- A tool or interface used to inspect, configure, or modify model-related assets such as prompts, adapters, metadata, or deployment settings. The term is usually...
- Model Efficiency
- How effectively a model uses compute, memory, and time to deliver useful performance for a given task. Model efficiency matters because a slightly less capable...
- Model Endpoint
- An API endpoint through which applications send requests to a specific model or model-backed service. Model endpoints often expose inference, embeddings,...
- Model Ensemble
- Model Ensemble is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model Error
- An error arising from model behavior, model execution, or model-based prediction rather than from ordinary application logic alone. Model errors may include...
- Model Eval
- An evaluation process or result used to measure how a model performs on chosen tasks, datasets, or business criteria. Teams rely on model evals to compare...
- Model Evaluation
- Model Evaluation is an evaluation concept used to measure model quality, robustness, or efficiency. It is commonly used for comparing systems before release or...
- Model Explainability
- Model Explainability is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model Family
- A related set of model versions or sizes built from the same underlying architecture or development line. Model families often share capabilities and...
- Model Fingerprint
- An identifier or signature used to distinguish a specific model build, configuration, or inference environment from others. Model fingerprints help trace...
- Model Format
- The file or representation format used to store, exchange, or load model weights and related metadata. Model format choices affect portability, performance,...
- Model Gateway
- A gateway layer that manages traffic to one or more models and often adds logging, policy enforcement, routing, authentication, and rate control. Model...
- Model Generation
- The output produced by a model, or in some contexts the act of generating that output from a prompt or input. The phrase is broad and typically refers to text,...
- Model Governance
- Model Governance is a safety or governance control for limiting harmful, noncompliant, or insecure model behavior. It is commonly used for production AI...
- Model Hosting
- The infrastructure and operational setup used to run and serve models, whether managed by a provider or self-hosted by a team. Model hosting affects cost,...
- Model Hub
- Model Hub is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model ID
- A specific identifier used to select or reference a model in code, configuration, or deployment systems. Model IDs are critical in production because closely...
- Model Inference
- Model Inference is the phase where a trained model processes new inputs to produce predictions or generations. It is commonly used for production APIs, batch...
- Model Input
- The data supplied to a model for processing, such as text, images, prompts, metadata, or retrieved context. Model input quality and structure strongly...
- Model Integration
- The work of connecting a model to an application, workflow, or platform so it can be used as part of a real product. Model integration includes APIs, prompts,...
- Model Interface
- The defined way other software or users interact with a model, including input shape, output structure, supported parameters, and behavioral expectations. A...
- Model Latency
- The delay introduced by the model portion of a system, from receiving input to producing output. Model latency is a key product metric because users notice...
- Model License
- The legal terms governing how a model can be used, modified, distributed, or commercialized. Model licenses matter because they can restrict deployment...
- Model Lifecycle
- The full life of a model from selection or training through evaluation, deployment, monitoring, updates, and retirement. Managing the model lifecycle well...
- Model Limit
- A practical or technical boundary on model behavior, such as context size, latency tolerance, modality support, or reliability under certain conditions....
- Model Merging
- Model Merging is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model Metric
- A metric used to measure some aspect of model behavior, such as accuracy, latency, cost, calibration, or acceptance rate. Model metrics are most useful when...
- Model Migration
- The process of moving a workflow or product from one model, model family, or serving setup to another. Model migrations require careful testing because subtle...
- Model Monitor
- A monitoring system or process used to track model quality, latency, safety, or drift over time. Model monitors help catch degradation that benchmarks and...
- Model Name
- The human-readable name used to refer to a model in product docs, configuration, or provider catalogs. Model names are useful, but engineering systems usually...
- Model Optimization
- Improving a model or its serving path for better quality, efficiency, speed, or cost through tuning, pruning, quantization, routing, or infrastructure changes....
- Model Output
- The result returned by a model after processing its input, whether as text, labels, scores, embeddings, images, or structured fields. Model output often needs...
- Model Parallelism
- Model Parallelism is a systems strategy for splitting model computation or parameters across devices. It is commonly used for training and serving workloads...
- Model Parameter
- A parameter within a model, or in product usage a configurable setting that affects model behavior. The term can refer either to learned weights or to external...
- Model Performance
- How well a model performs on the dimensions that matter for a task, such as accuracy, speed, cost, robustness, or user satisfaction. Model performance should...
- Model Pipeline
- A pipeline built around a model, including input preparation, inference, post-processing, logging, and any supporting retrieval or validation steps. Model...
- Model Platform
- A shared platform that standardizes how teams discover, evaluate, deploy, and monitor models. Model platforms reduce duplicated infrastructure work and help...
- Model Plugin
- A plugin that adds model-related capabilities to a product, or a modular model component integrated into a larger system. The exact meaning depends on the...
- Model Poisoning
- Model Poisoning is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model Prediction
- A prediction or output produced by a model based on its input. The term is common in both classic machine learning and modern generative systems, though in...
- Model Pruning
- Model Pruning is a compression technique that removes parameters, channels, or structures judged less important. It is commonly used for shrinking models for...
- Model Quality
- The overall usefulness and reliability of a model's outputs for the intended task, considering correctness, consistency, safety, and user acceptance. Model...
- Model Quantization
- Model Quantization is a technique that reduces numerical precision so models use less memory and compute. It is commonly used for deploying large models on...
- Model Registry
- Model Registry is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model Release
- A released version of a model made available for testing or production use. Model releases may include updated weights, changed behavior, new limits, or...
- Model Request
- A single request sent to a model or model-backed endpoint, including input data and relevant settings. Tracking model requests is important for debugging,...
- Model Response
- The response returned by a model after processing a request. Depending on the system, a model response may include text, scores, embeddings, tool calls, or...
- Model Safety
- The set of behaviors, controls, and evaluation practices aimed at preventing harmful, unsafe, or policy-violating model outputs and actions. Model safety work...
- Model Scale
- The size or operational scale of a model, whether measured in parameter count, context length, throughput, or production traffic. Model scale shapes...
- Model SDK
- A software development kit that helps applications interact with models through typed calls, retries, streaming helpers, and consistent request handling. Model...
- Model Selection
- The process of choosing which model is best suited for a task, product, or request based on quality, speed, cost, safety, and operational constraints. Model...
- Model Server
- A server or service instance that loads a model and handles inference requests against it. Model servers may support batching, scaling, caching, and health...
- Model Serving Detail
- Model Serving Detail is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model Sharding
- Model Sharding is a systems strategy for splitting model computation or parameters across devices. It is commonly used for training and serving workloads that...
- Model Size
- The scale of a model, usually discussed in terms of parameter count, memory footprint, or checkpoint size. Model size affects latency, hardware requirements,...
- Model Speed
- The speed at which a model can return results, often measured by latency or tokens per second. Model speed matters especially in interactive products where...
- Model Stacking
- Model Stacking is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model State
- The current state associated with a model or model session, such as loaded weights, cached context, runtime settings, or internal serving condition. The exact...
- Model Streaming
- The incremental delivery of model output as it is produced rather than returning only a completed result at the end. Model streaming improves perceived...
- Model Temperature
- The temperature setting applied during generation to make output more deterministic or more varied. Higher temperature generally increases randomness, while...
- Model Test
- A test case or testing process used to check model behavior, quality, safety, or performance. Model tests are often included in regression suites before...
- Model Token
- A token as understood by a model's tokenizer and counted for context limits, billing, or generation length. Model token behavior matters because different...
- Model Tokenizer
- The tokenizer associated with a model that converts raw input into tokens and often converts generated tokens back into text. The tokenizer affects context...
- Model Tool
- A tool used to work with models, or a callable tool made available to a model system so it can do more than generate text alone. The exact meaning depends on...
- Model Trace
- A detailed record of how a model request was processed, including input assembly, retrieval steps, inference timing, tool interactions, and validation results....
- Model Training
- Model Training is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for foundation-model...
- Model Update
- An update to a model, its configuration, or its surrounding serving behavior. Model updates can improve quality or capability, but they also introduce...
- Model Usage
- How frequently and in what ways a model is used across products, teams, or workflows. Tracking model usage helps with cost control, capacity planning, and...
- Model Validation
- The process of verifying that a model or model-backed system behaves acceptably before or during deployment. Model validation can include benchmarks,...
- Model Version
- A specific version of a model distinguished from earlier or later versions by weights, configuration, or release status. Explicit model versioning is essential...
- Model Versioning
- Model Versioning is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Model Weight
- A learned numerical parameter in a model that influences how inputs are transformed into outputs. Collectively, model weights encode much of the behavior...
- Model Zoo
- Model Zoo is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Monte Carlo Dropout
- Monte Carlo Dropout is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- Monte Carlo Tree Search
- Monte Carlo Tree Search is a retrieval or nearest-neighbor concept for efficiently finding relevant items in large spaces. It is commonly used for semantic...
- Morphological Analysis
- Morphological Analysis is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- Moshi
- Moshi is a real-time speech-native model architecture aimed at low-latency spoken interaction. It is commonly used for voice assistants and conversational...
- Motion Capture AI
- Motion Capture AI is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Multi-Agent System
- Multi-Agent System is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Multi-GPU Training
- Multi-GPU Training is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for foundation-model...
- Multi-Head Attention
- Multi-Head Attention is a mechanism that weights the most relevant tokens, positions, or features during computation. It is commonly used for transformers and...
- Multi-Label Classification
- Multi-Label Classification is a modeling approach for assigning one or more labels to an input. It is commonly used for ranking, triage, moderation, and...
- Multi-Modal Fusion
- Multi-Modal Fusion is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Multimodal Learning
- Multimodal Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Multi-Task Learning
- Multi-Task Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Mutual Information
- Mutual Information is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Naive Bayes
- Naive Bayes is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Nearest Neighbor Search
- Nearest Neighbor Search is a retrieval or nearest-neighbor concept for efficiently finding relevant items in large spaces. It is commonly used for semantic...
- Negative Sampling
- Negative Sampling is a decoding control that shapes how a generative model selects its next output. It is commonly used for text and multimodal generation...
- Neural Architecture Search
- Neural Architecture Search is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building...
- Neural Network Detail
- Neural Network Detail is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Neural ODE
- Neural ODE is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Neural Style Transfer
- Neural Style Transfer is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- Noise Contrastive Estimation
- Noise Contrastive Estimation is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production...
- Noise Schedule
- Noise Schedule is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Non-Autoregressive Model
- Non-Autoregressive Model is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building...
- Normalization Layer
- Normalization Layer is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Nucleus Sampling
- Nucleus Sampling is a decoding control that shapes how a generative model selects its next output. It is commonly used for text and multimodal generation...
- Number Theory ML
- Number Theory ML is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- One-Hot Encoding
- One-Hot Encoding is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- One-Shot Learning
- One-Shot Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Online Learning
- Online Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- OpenAI Codex
- OpenAI's coding-oriented model and product line associated with code generation, editing, and software-task assistance.
- Open Source AI
- AI systems, models, tools, or related assets released under terms that allow inspection, modification, and reuse to some degree. The phrase is often debated...
- Open Source Model
- Open Source Model is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Open Weight
- An AI model whose trained weights are publicly released, allowing anyone to run, fine-tune, or build upon it. Distinct from truly 'open source' because the...
- Open Weight Model
- Open Weight Model is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Optimal Transport
- Optimal Transport is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Outlier Detection
- Outlier Detection is an application task where a model extracts structured meaning or predictions from raw input. It is commonly used for NLP and vision...
- Overfit
- Overfit is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Parameter Count
- The total number of learned parameters in a model, commonly used as a rough indicator of size and sometimes capability. Parameter count is informative, but it...
- PEFT
- PEFT is parameter-efficient fine-tuning methods that update only a small subset of model parameters. It is commonly used for customizing large models without...
- Perception Module
- Perception Module is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Perceptron
- Perceptron is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Permutation Invariance
- Permutation Invariance is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- Personalization
- Personalization is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Pixel Shuffle
- Pixel Shuffle is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Pooling Layer
- Pooling Layer is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Position Encoding
- Position Encoding is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Post-Training
- Post-Training is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for foundation-model...
- Preference Learning
- Preference Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Preference Model
- A model trained to predict or score human preferences among candidate outputs, often used in alignment and reinforcement learning pipelines. Preference models...
- Prefix Tuning
- Prefix Tuning is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Pre-Training
- Pre-Training is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for foundation-model...
- Pretraining Data
- Pretraining Data is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for foundation-model...
- Principal Component Analysis
- Principal Component Analysis is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production...
- Probabilistic Model
- Probabilistic Model is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Probability Distribution
- Probability Distribution is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production...
- Protein Folding AI
- Protein Folding AI is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- QLoRA
- QLoRA is a parameter-efficient fine-tuning method that combines low-rank adapters with quantized base weights. It is commonly used for adapting large language...
- Quantization Aware Training
- Quantization Aware Training is a technique that reduces numerical precision so models use less memory and compute. It is commonly used for deploying large...
- Question Answering
- Question Answering is an application task where a model extracts structured meaning or predictions from raw input. It is commonly used for NLP and vision...
- RAFT
- RAFT is a dense optical-flow architecture based on recurrent all-pairs field transforms. It is commonly used for estimating pixel-level motion between video...
- Random Forest
- Random Forest is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Random Search
- Random Search is a retrieval or nearest-neighbor concept for efficiently finding relevant items in large spaces. It is commonly used for semantic search,...
- Rank Fusion
- Rank Fusion is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Ranking Model
- A model used to score and order candidate items such as documents, answers, ads, or recommendations according to relevance or quality. Ranking models are...
- Reasoning
- Reasoning is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Reasoning Chain
- Reasoning Chain is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Reasoning Model
- A model optimized or selected for tasks that require stronger multi-step inference, planning, or problem decomposition rather than simple pattern matching...
- Receptive Field
- Receptive Field is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Recommendation System
- Recommendation System is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- Recurrent Neural Network
- Recurrent Neural Network is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building...
- Regression
- Regression is a supervised learning method for estimating numeric outputs from input features. It is commonly used for prediction pipelines and baseline...
- Representation
- The encoded form in which a model captures information about inputs, concepts, or patterns internally. Representations shape what distinctions the model can...
- Representation Learning
- Representation Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Residual Connection
- Residual Connection is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- Residual Network
- Residual Network is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Retrieval Model
- A model used to retrieve relevant information, often by creating embeddings, ranking candidates, or estimating semantic similarity. Retrieval models are...
- Ring Attention
- Ring Attention is a mechanism that weights the most relevant tokens, positions, or features during computation. It is commonly used for transformers and...
- RLHF Detail
- RLHF Detail is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- RNN
- RNN is a recurrent neural network that reuses state across time steps. It is commonly used for language, audio, and time-series sequence modeling, where teams...
- Running Average
- Running Average is a training-time optimization concept that governs how model parameters are updated. It is commonly used for iterative learning loops for...
- Sample Efficiency
- Sample Efficiency is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Sampling Strategy
- Sampling Strategy is a decoding control that shapes how a generative model selects its next output. It is commonly used for text and multimodal generation...
- Sampling Temperature
- Sampling Temperature is a decoding control that shapes how a generative model selects its next output. It is commonly used for text and multimodal generation...
- Scalar Quantization
- Scalar Quantization is a technique that reduces numerical precision so models use less memory and compute. It is commonly used for deploying large models on...
- Scheduled Sampling
- Scheduled Sampling is a decoding control that shapes how a generative model selects its next output. It is commonly used for text and multimodal generation...
- Score Matching
- Score Matching is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Scoring Model
- A model used to score candidates, outputs, or states according to relevance, quality, safety, or another target property. Scoring models are common in ranking,...
- Self-Attention
- Self-Attention is a mechanism that weights the most relevant tokens, positions, or features during computation. It is commonly used for transformers and...
- Self-Play
- Self-Play is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Self-Supervised Learning
- Self-Supervised Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Semantic Similarity
- Semantic Similarity is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- Semi-Supervised Learning
- Semi-Supervised Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Sequence Model
- A model designed to process ordered sequences such as text, audio, or time-series data while accounting for order and context. Sequence models include...
- SGD
- SGD is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- SIGLIP
- SIGLIP is a vision-language model family trained with sigmoid contrastive objectives instead of softmax normalization. It is commonly used for image-text...
- Sigmoid
- Sigmoid is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Similarity Search
- Similarity Search is a retrieval or nearest-neighbor concept for efficiently finding relevant items in large spaces. It is commonly used for semantic search,...
- Skip Connection
- Skip Connection is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Softmax
- Softmax is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Sparse Attention
- Sparse Attention is a mechanism that weights the most relevant tokens, positions, or features during computation. It is commonly used for transformers and...
- Sparse Mixture of Experts
- Sparse Mixture of Experts is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production...
- Sparse Model
- A model in which only a subset of parameters or pathways are active for a given input, rather than using the full parameter set every time. Sparse models can...
- Sparse Retrieval
- Sparse Retrieval is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Speculative Decoding
- Speculative Decoding is a decoding control that shapes how a generative model selects its next output. It is commonly used for text and multimodal generation...
- State Space Model
- State Space Model is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Stemming
- Stemming is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Step Function
- Step Function is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Stride
- Stride is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Strong AI
- Strong AI is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Student Model
- A smaller or simpler model trained to imitate or approximate the behavior of a larger teacher model. Student models are often used to reduce cost and latency...
- Style Transfer
- Style Transfer is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Summarization
- Summarization is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Supervised Fine-Tuning
- Supervised Fine-Tuning is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for foundation-model...
- Supervised Learning
- Supervised Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Surrogate Model
- A simpler or cheaper model used to approximate a more expensive process, objective, or system during optimization or experimentation. Surrogate models help...
- Synthetic Data Generation
- Synthetic Data Generation is a generative modeling concept for producing new content such as text, images, audio, or video. It is commonly used for creative...
- System 1 and System 2
- System 1 and System 2 is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- Tabular Learning
- Tabular Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Teacher Forcing
- Teacher Forcing is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Teacher Model
- Teacher Model is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Temperature Scaling
- Temperature Scaling is a decoding control that shapes how a generative model selects its next output. It is commonly used for text and multimodal generation...
- Temporal Difference Learning
- Temporal Difference Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that...
- Test-Time Compute
- Test-Time Compute is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Text Classification
- Text Classification is a modeling approach for assigning one or more labels to an input. It is commonly used for ranking, triage, moderation, and structured...
- Text Generation
- Text Generation is a generative modeling concept for producing new content such as text, images, audio, or video. It is commonly used for creative tools,...
- Text-to-SQL
- Text-to-SQL is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- TFDS
- TFDS is TensorFlow Datasets, a curated collection of ready-to-load datasets and dataset loaders. It is commonly used for standardized benchmarking and...
- Tool Use Detail
- Tool Use Detail is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Top-K Sampling
- Top-K Sampling is a decoding control that shapes how a generative model selects its next output. It is commonly used for text and multimodal generation systems...
- Top-P Sampling
- Top-P Sampling is a decoding control that shapes how a generative model selects its next output. It is commonly used for text and multimodal generation systems...
- Training Compute
- Training Compute is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for foundation-model...
- Training Data Detail
- Training Data Detail is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for foundation-model...
- Training Loop
- Training Loop is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for foundation-model...
- Training Run
- Training Run is a stage of model optimization where weights or behaviors are adjusted from data or feedback. It is commonly used for foundation-model...
- Transfer Learning
- Transfer Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Transformer Architecture
- Transformer Architecture is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building...
- Transformer Block
- Transformer Block is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Transformer Decoder
- Transformer Decoder is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Transformer Encoder
- Transformer Encoder is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- Tree of Thought
- Tree of Thought is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Truncation
- Truncation is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Tuning
- Tuning is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Turing Award
- Turing Award is the highest-profile award in computer science, often compared with a Nobel Prize for the field. It is commonly used for recognizing...
- Underfitting
- Underfitting is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- U-Net
- U-Net is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Unlabeled Data
- Unlabeled Data is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Unsupervised Learning
- Unsupervised Learning is a learning paradigm that improves task performance from data, feedback, or experience. It is commonly used for models that adapt...
- Upsampling
- Upsampling is a decoding control that shapes how a generative model selects its next output. It is commonly used for text and multimodal generation systems...
- VAE
- VAE is a probabilistic generative model that learns a continuous latent space with variational objectives. It is commonly used for representation learning,...
- Validation Set
- Validation Set is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Value Function
- Value Function is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Variational Autoencoder
- Variational Autoencoder is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building...
- Variational Inference
- Variational Inference is the phase where a trained model processes new inputs to produce predictions or generations. It is commonly used for production APIs,...
- Vector Index
- Vector Index is a retrieval or nearest-neighbor concept for efficiently finding relevant items in large spaces. It is commonly used for semantic search,...
- Vector Quantization
- Vector Quantization is a technique that reduces numerical precision so models use less memory and compute. It is commonly used for deploying large models on...
- Vector Search
- Vector Search is a retrieval or nearest-neighbor concept for efficiently finding relevant items in large spaces. It is commonly used for semantic search,...
- Vision Model
- A model designed to process images or visual data for tasks such as classification, detection, captioning, OCR, or multimodal reasoning. Vision models are...
- Visual Question Answering
- Visual Question Answering is an application task where a model extracts structured meaning or predictions from raw input. It is commonly used for NLP and...
- Vocabulary
- Vocabulary is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Weak AI
- Weak AI is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Weight
- Weight is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Weight Decay
- Weight Decay is a training-time optimization concept that governs how model parameters are updated. It is commonly used for iterative learning loops for neural...
- Weight Initialization
- Weight Initialization is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models...
- Weight Merging
- Combining weights or learned parameter changes from multiple models, adapters, or fine-tunes to produce a merged model. Weight merging is explored as a way to...
- Weight Sharing
- Weight Sharing is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- Weight Tying
- Weight Tying is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and...
- World Knowledge
- General knowledge about facts, concepts, and regularities in the world that a model has learned or can access. World knowledge differs from task-specific or...
- World Model
- World Model is a model component or design choice that shapes how information flows through a learned system. It is commonly used for building neural...
- XGBoost
- XGBoost is an AI or ML concept used to represent, train, evaluate, or deploy learned systems. It is commonly used for building production models and research...
- Zero-Shot Classification
- Zero-Shot Classification is a modeling approach for assigning one or more labels to an input. It is commonly used for ranking, triage, moderation, and...
Related Topics
- Ai (264 terms in common)
- Ml (159 terms in common)
- Deployment (43 terms in common)
- Mlops (42 terms in common)
- Architecture (17 terms in common)
- Parameters (3 terms in common)
- Performance (2 terms in common)
- Tooling (2 terms in common)
- Platforms (2 terms in common)
- Open Source (2 terms in common)
- Context Windows (2 terms in common)
- Optimization (2 terms in common)
- Scale (2 terms in common)
- Licensing (2 terms in common)
- Weights (2 terms in common)
- Efficiency (2 terms in common)
- Representations (2 terms in common)
- Apis (2 terms in common)
- Versioning (2 terms in common)
- Versions (1 terms in common)