Skip to main content
Zubnet AI › Learn › Wiki

AI Wiki — Page 6 of 10

AI concepts explained by builders, not textbooks. No jargon walls. No academic gatekeeping. Just clear, practical definitions of the terms you'll actually encounter.

454 terms 8 categories Updated 2026-11-22
💡
Term of the Day
Deepgram
Speech AI company building fast, accurate speech recognition and text-to-speech APIs. Their Nova models compete with and often beat OpenAI's Whisper…
→
No terms on this page match your filters.

251–300 of 454 terms · Page 6 of 10

Filter this page

Machine UnlearningAlso known as: Unlearning, LLM Unlearning
Training
Techniques for making a trained model forget specific data or knowledge without retraining it from scratch.
MambaMamba Architecture
Models
A selective state space model (SSM) architecture designed as an alternative to the Transformer. Created by Albert Gu…
Masked Language ModelingMLM, Masked LM, Cloze Task
Training
A self-supervised training objective where random tokens in the input are replaced with a [MASK] token, and the model…
Fundamentals
The fundamental mathematical operation underlying all neural networks. Multiplying a weight matrix by an input vector…
MCPAlso known as: Model Context Protocol
Tools
An open protocol (created by Anthropic) that standardizes how AI models connect to external tools and data sources.…
Safety
A research approach that tries to understand what's happening inside neural networks at the level of individual…
MemoryAlso known as: AI Memory, Persistent Context
Using AI
Mechanisms that allow AI models to retain and recall information beyond a single conversation. This includes…
Meta AIAlso known as: Llama, FAIR
Companies
Meta's AI research division, home of FAIR (Fundamental AI Research). Responsible for the open-weights Llama model…
MicrosoftAlso known as: Microsoft AI, Azure AI
Companies
The software giant behind Copilot, Azure and the Phi models, and OpenAI's largest early backer.
Companies
An AI image generation company known for producing some of the most aesthetically refined AI-generated images. Unlike…
MiniMaxAlso known as: MiniMax models, Hailuo AI, video generation
Companies
Chinese AI company building large-scale models across text, voice, and video. Known for their Hailuo consumer platform…
Mistral AIAlso known as: Mistral, Mixtral, Codestral, Le Chat
Companies
European AI powerhouse founded by former DeepMind and Meta researchers. Known for punching above their weight with…
Mixed Precision TrainingFP16, BF16, Half Precision
Training
Training neural networks using lower-precision number formats (16-bit instead of 32-bit) for most computations while…
MLAAlso known as: Multi-head Latent Attention
Models
DeepSeek's attention design that stores a small compressed vector per token instead of full keys and values, shrinking…
MLXAlso known as: MLX-LM, Apple MLX
Tools
Apple's open-source machine learning framework for Apple Silicon, widely used to run and fine-tune models locally on…
MMLUAlso known as: Massive Multitask Language Understanding, MMLU-Pro, GPQA
Training
A multiple-choice exam of about 16,000 questions across 57 subjects that was the standard measure of an LLM's general…
ModelAlso known as: AI Model, ML Model
Fundamentals
A trained mathematical system that takes inputs and produces outputs based on patterns learned from data. In AI,…
Model CardModel Documentation, Data Sheet
Safety
A standardized document that describes a machine learning model's intended use, performance characteristics, training…
Model CollapseData Feedback Loop
Training
The degradation that occurs when AI models are trained on data generated by previous AI models, creating a feedback…
Model MergingTIES, DARE, SLERP, Frankenmerge
Training
Combining the weights of multiple fine-tuned models into a single model without any additional training. If model A is…
Model RegistryModel Store, Model Catalog
Infrastructure
A centralized system for versioning, tracking, and managing trained machine learning models throughout their…
Model ServingvLLM, TGI, TensorRT-LLM, Inference Server
Infrastructure
The infrastructure and software that runs trained AI models in production, handling incoming requests, managing GPU…
Mixture of ExpertsAlso known as: MoE
Models
An architecture where the model contains multiple "expert" sub-networks, but only activates a few of them for each…
Moonshot AIAlso known as: Kimi, ultra-long context models
Companies
Chinese AI company that made waves by launching Kimi, a chatbot with a 2-million-token context window. Founded by Yang…
Multi-Agent SystemsMulti-Agent, Agent Swarm
Using AI
Architectures where multiple AI agents collaborate, debate, or specialize to solve problems that a single agent can't…
Fundamentals
Running multiple attention operations in parallel, each with its own learned projection of the queries, keys, and…
Multi-Query AttentionAlso known as: MQA
Models
An attention design where all query heads share a single set of keys and values, shrinking the KV cache and speeding…
Fundamentals
A model that can understand and/or generate multiple types of data: text, images, audio, video, code. Claude can read…
Music GenerationAI Music, Text-to-Music
Using AI
Creating music from text descriptions, melodies, or other audio inputs using AI models. "An upbeat electronic track…
Needle in a HaystackAlso known as: NIAH, Needle Test
Training
A long-context test that hides one small fact inside a very long document and checks whether the model can find it.
Negative PromptNegative Conditioning
Using AI
A text description of what you don't want in a generated image, used alongside the main prompt. Prompt: "a beautiful…
Named Entity RecognitionNER, Entity Extraction
Using AI
Identifying and categorizing named entities in text — people, organizations, locations, dates, monetary amounts, and…
Fundamentals
A computing system loosely inspired by biological brains, made of layers of interconnected "neurons" (mathematical…
NeuronArtificial Neuron, Perceptron, Node
Fundamentals
The basic computational unit of a neural network. An artificial neuron receives inputs, multiplies each by a weight,…
Natural Language ProcessingAlso known as: NLP
Fundamentals
The branch of AI focused on enabling machines to understand, interpret, and generate human language. NLP covers…
NormalizationLayerNorm, RMSNorm, BatchNorm
Training
Techniques that stabilize neural network training by normalizing the values flowing through the network to have…
NPUAlso known as: Neural Processing Unit, AI Accelerator
Infrastructure
A chip, or part of a chip, built specifically to run neural networks efficiently, found in phones, laptops and other…
NVIDIAAlso known as: GPUs, H100/H200, NeMo
Companies
The company whose GPUs power virtually all AI training and most inference worldwide. What started as a graphics card…
Object DetectionBounding Box Detection
Using AI
Identifying and localizing objects in images or video by drawing bounding boxes around them and classifying what each…
OCROptical Character Recognition, Text Recognition
Using AI
Extracting text from images — photographs of documents, screenshots, signs, handwritten notes, or any image containing…
Tools
A user-friendly tool for running language models locally with a single command. Ollama wraps llama.cpp in a…
ONNXOpen Neural Network Exchange
Infrastructure
An open format for representing machine learning models that enables interoperability between frameworks. A model…
Open vs. ClosedOpen Source vs. Proprietary, Open Weights Debate
Fundamentals
The ongoing debate about whether AI models should be openly released (weights publicly available, like Llama and…
Open WeightsAlso known as: Open Source (in AI context)
Safety
When a company releases a model's trained parameters for anyone to download and run. "Open weights" is more accurate…
OpenAIAlso known as: GPT, ChatGPT, DALL-E, Sora
Companies
The company behind ChatGPT and the GPT series of models. Originally a non-profit research lab, OpenAI became the…
OpenAI-Compatible APIAlso known as: OpenAI-Compatible Endpoint, Chat Completions API
Infrastructure
An API that copies the request and response format of OpenAI's Chat Completions endpoint, so existing OpenAI client…
Companies
A unified API gateway that gives developers access to hundreds of large language models from different providers…
OptimizationAlso known as: Model Optimization, Inference Optimization
Training
The broad set of techniques used to make AI models faster, smaller, cheaper, or more accurate. This includes training…
Training
When a model memorizes its training data too well and loses the ability to generalize to new inputs. Like a student…
Infrastructure
A memory management technique for KV cache that borrows from operating system virtual memory. Instead of allocating a…
ESC