Results for "language"

Language Model

Intermediate

A model that assigns probabilities to sequences of tokens; often trained by next-token prediction.

A language model is like a smart assistant that predicts what word comes next in a sentence based on the words that came before it. Imagine you’re playing a word game where you have to guess the next word in a sentence. The model learns from a huge amount of text, like books and articles, to unde...

AdvertisementAd space — search-top

79 results

Recurrent Neural Network Intermediate

Networks with recurrent connections for sequences; largely supplanted by Transformers for many tasks.

Neural Networks
Positional Encoding Intermediate

Injects sequence order into Transformers, since attention alone is permutation-invariant.

Foundations & Theory
LSTM Intermediate

An RNN variant using gates to mitigate vanishing gradients and capture longer context.

Foundations & Theory
Tokenization Intermediate

Converting text into discrete units (tokens) for modeling; subword tokenizers balance vocabulary size and coverage.

Foundations & Theory
Transformer Intermediate

Architecture based on self-attention and feedforward layers; foundation of modern LLMs and many multimodal models.

Transformers & LLMs
Next-Token Prediction Intermediate

Training objective where the model predicts the next token given previous tokens (causal modeling).

Foundations & Theory
Autoregressive Model Intermediate

Generates sequences one token at a time, conditioning on past tokens.

Foundations & Theory
Vector Database Intermediate

A datastore optimized for similarity search over embeddings, enabling semantic retrieval at scale.

Large Language Models
Semantic Search Intermediate

Retrieval based on embedding similarity rather than keyword overlap, capturing paraphrases and related concepts.

Foundations & Theory
Data Augmentation Intermediate

Expanding training data via transformations (flips, noise, paraphrases) to improve robustness.

Foundations & Theory
Beam Search Intermediate

Search algorithm for generation that keeps top-k partial sequences; can improve likelihood but reduce diversity.

Foundations & Theory
Temperature Intermediate

Scales logits before sampling; higher increases randomness/diversity, lower increases determinism.

Foundations & Theory
Top-k Intermediate

Samples from the k highest-probability tokens to limit unlikely outputs.

Foundations & Theory
Top-p Intermediate

Samples from the smallest set of tokens whose probabilities sum to p, adapting set size by context.

Foundations & Theory
Softmax Intermediate

Converts logits to probabilities by exponentiation and normalization; common in classification and LMs.

Foundations & Theory
Benchmark Intermediate

A dataset + metric suite for comparing models; can be gamed or misaligned with real-world goals.

Evaluation & Benchmarking
Prompt Injection Intermediate

Attacks that manipulate model instructions (especially via retrieved content) to override system goals or exfiltrate data.

Foundations & Theory
Planning Intermediate

Methods for breaking goals into steps; can be classical (A*, STRIPS) or LLM-driven with tool calls.

Foundations & Theory
Text-to-Speech Intermediate

Generating speech audio from text, with control over prosody, speaker identity, and style.

Speech & Audio AI
Causal Mask Intermediate

Prevents attention to future tokens during training/inference.

AI Economics & Strategy
Multi-Head Attention Intermediate

Allows model to attend to information from different subspaces simultaneously.

AI Economics & Strategy
Sparse Attention Intermediate

Attention mechanisms that reduce quadratic complexity.

AI Economics & Strategy
Mixture of Experts Intermediate

Routes inputs to subsets of parameters for scalable capacity.

AI Economics & Strategy
Emergent Abilities Intermediate

Capabilities that appear only beyond certain model sizes.

AI Economics & Strategy
Knowledge Graph Intermediate

Structured graph encoding facts as entity–relation–entity triples.

Model Architectures
Conditional Random Field Intermediate

Probabilistic graphical model for structured prediction.

Model Architectures
Vision Transformer Intermediate

Transformer applied to image patches.

Computer Vision
Speech Synthesis Intermediate

Generating human-like speech from text.

Speech & Audio AI
Acoustic Model Intermediate

Maps audio signals to linguistic units.

Speech & Audio AI
Speaker Diarization Intermediate

Identifying speakers in audio.

Speech & Audio AI

Welcome to AI Glossary

The free, self-building AI dictionary. Help us keep it free—click an ad once in a while!

Search

Type any question or keyword into the search bar at the top.

Browse

Tap a letter in the A–Z bar to browse terms alphabetically, or filter by domain, industry, or difficulty level.

3D WordGraph

Fly around the interactive 3D graph to explore how AI concepts connect. Click any word to read its full definition.