Skip to main content
Zubnet AI › Learn › Wiki

AI Wiki — Page 5 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.

201–250 of 454 terms · Page 5 of 10

Filter this page

Hyperparameter TuningHPO, Hyperparameter Optimization, Grid Search
Training
Systematically searching for the best hyperparameters — the configuration choices that aren't learned during training…
HyperparametersAlso known as: Training Hyperparameters
Training
Settings you choose before training begins that control how the model learns — as opposed to parameters, which the…
IBMAlso known as: International Business Machines, watsonx
Companies
One of the oldest names in computing and AI, now focused on enterprise AI with its watsonx platform, open Granite…
IdeogramAlso known as: Text rendering in images, Ideogram 2.0
Companies
AI image generation company founded by former Google Brain researchers. Made their name by solving one of the hardest…
Image GenerationText-to-Image, AI Art
Fundamentals
Creating images from text descriptions using AI models. You type "a sunset over mountains in watercolor style" and the…
Image SegmentationSemantic Segmentation, SAM, Instance Segmentation
Using AI
Classifying every pixel in an image into a category. Semantic segmentation labels pixels by class (road, sidewalk,…
ImagenAlso known as: Gemini Image
Models
Google's line of image generation models, from the Imagen diffusion models to the conversational Gemini image models…
ImageNetAlso known as: ImageNet Challenge, ILSVRC
Training
A large-scale image dataset of roughly 14 million hand-labeled images organized into more than 20,000 categories,…
Image-to-Imageimg2img, Image Conditioning
Using AI
Generating a new image based on an existing image plus a text prompt. Instead of starting from pure noise…
In-Context LearningAlso known as: ICL
Fundamentals
The ability of a large language model to pick up a task from examples or instructions placed in the prompt, with no…
Fundamentals
A specific two-attention-head circuit discovered in Transformers that implements in-context learning by pattern…
Infrastructure
The process of running a trained model to generate outputs. Training is learning; inference is using what was learned.…
Inflection AIAlso known as: Inflection, Pi
Companies
An AI company founded in 2022 by Mustafa Suleyman, Reid Hoffman, and Karén Simonyan, best known for Pi, a personal…
Information ExtractionIE, Structured Extraction
Using AI
Automatically extracting structured information from unstructured text. Given a news article, extract: who did what,…
InpaintingImage Inpainting, Outpainting
Using AI
Filling in a selected region of an image with AI-generated content that matches the surrounding context. You mask an…
Instruction FollowingInstruction Adherence
Using AI
A model's ability to accurately execute what the user asks for — respecting format constraints, length requirements,…
Instruction TuningInstruction Fine-Tuning, IFT
Training
Fine-tuning a pre-trained language model on a dataset of (instruction, response) pairs to teach it to follow…
InterpretabilityAlso known as: Explainability, Explainable AI
Safety
The effort to understand why an AI model produces the outputs it does, by explaining its decisions or examining its…
JailbreakJailbreaking, Adversarial Prompt
Safety
Techniques that trick an AI model into bypassing its safety training and generating content it was designed to refuse…
JAXAlso known as: Google JAX
Tools
Google's Python library for high-performance numerical computing, combining a NumPy-like API with automatic…
Jina AIAlso known as: Embeddings, Reader API, rerankers
Companies
Berlin-based AI company specializing in search and embeddings. Their jina-embeddings models and Reader API (which…
Kling AIAlso known as: Kling video generation, long-form video
Companies
AI video platform from Kuaishou (China's second-largest short-video platform). Gained rapid international attention…
Knowledge CutoffTraining Data Cutoff, Knowledge Date
Fundamentals
The date after which a model has no training data, meaning it lacks knowledge of events, discoveries, or changes that…
Knowledge EditingModel Editing, Fact Editing
Training
Techniques for modifying specific facts in a trained model without retraining it. If a model incorrectly states "The…
Knowledge GraphKG, Ontology
Fundamentals
A structured representation of knowledge as a network of entities (nodes) connected by relationships (edges). "Paris…
KV CacheKey-Value Cache
Infrastructure
A memory optimization that stores the previously computed key and value tensors from the attention mechanism so they…
Lambda LabsLambda, Lambda Cloud
Companies
A GPU cloud provider focused specifically on AI and machine learning workloads. Lambda offers on-demand and reserved…
Tools
A popular open-source framework for building applications with language models. LangChain provides abstractions for…
Language DetectionLanguage Identification, LangID
Using AI
Automatically identifying which language a text is written in. "Bonjour le monde" → French. "こんにちは世界" → Japanese.…
LatencyAlso known as: Time to First Token (TTFT)
Infrastructure
The delay between sending a request and getting the first response. In AI, this is often measured as Time to First…
Latent SpaceAlso known as: Latent Representation, Embedding Space
Fundamentals
The compressed internal space where a model represents data as points, with similar things placed close together.
LayerHidden Layer, Neural Network Layer
Fundamentals
A group of neurons that processes data at a specific level of abstraction in a neural network. The input layer…
Learning RateAlso known as: LR, Step Size
Training
The number that sets how big a step the optimizer takes on each update, and the single most important training…
Learning Rate ScheduleLR Schedule, Warmup, Cosine Annealing
Training
A strategy for changing the learning rate during training rather than keeping it constant. Most modern training uses…
Leonardo.aiAlso known as: Creative image generation, game asset creation
Companies
Australian AI image platform that carved out a niche between Midjourney and Stable Diffusion. Popular with game…
Lethal TrifectaAlso known as: Agents Rule of Two
Safety
The combination of access to private data, exposure to untrusted content and the ability to communicate externally,…
Liquid AIAlso known as: Liquid Foundation Models, liquid neural networks
Companies
MIT spinout exploring fundamentally different neural network architectures inspired by biological neural circuits.…
LlamaAlso known as: LLaMA, Meta Llama
Models
A family of large language models from Meta whose weights are freely downloadable under a custom community license.…
Tools
An open-source C/C++ library for running LLM inference on consumer hardware, created by Georgi Gerganov. llama.cpp…
LlamaIndexAlso known as: GPT Index
Tools
An open-source data framework for building LLM applications over private data. LlamaIndex handles the plumbing between…
Large Language ModelAlso known as: LLM
Fundamentals
A neural network trained on massive amounts of text to understand and generate human language. "Large" refers to the…
LLM-as-JudgeAlso known as: LLM Judge, LLM-as-a-Judge
Training
An evaluation technique where a large language model grades the outputs of another model (or its own) instead of…
LM StudioAlso known as: LMStudio
Tools
A desktop app for finding, downloading and running open language models locally, with a chat interface and a built-in…
LogitsRaw Scores, Pre-Softmax Outputs
Fundamentals
The raw, unnormalized scores that a model outputs before they're converted into probabilities by the softmax function.…
LoRAAlso known as: Low-Rank Adaptation
Training
A technique that makes fine-tuning dramatically cheaper by only training a small number of additional parameters…
Loss FunctionObjective Function, Cost Function
Training
A mathematical function that measures how wrong a model's predictions are. The model's entire goal during training is…
LSTMLong Short-Term Memory
Models
A type of recurrent neural network (RNN) designed to learn long-range dependencies in sequential data. LSTM introduces…
Luma AIAlso known as: Dream Machine, Ray2
Companies
AI company focused on video and 3D generation. Their Dream Machine was one of the first accessible, high-quality AI…
Machine LearningAlso known as: ML
Fundamentals
The broad field of computer science where systems learn patterns from data rather than following explicit rules.…
Machine TranslationMT, Neural Machine Translation, NMT
Using AI
Automatically translating text from one language to another. Modern neural machine translation (NMT) uses…
ESC