The Complete AI Dictionary
Master AI terminology from A to Z. 75 essential terms explained clearly, with real-world examples and connections to AI tools.
Featured Terms
AI Agent
An autonomous AI system that can perceive its environment, make decisions, and take actions to achieve specific goals.
AI Alignment
The challenge of ensuring AI systems behave in accordance with human intentions, values, and goals.
Artificial Intelligence(AI)
The simulation of human intelligence processes by computer systems, including learning, reasoning, and self-correction.
Bias in AI
Systematic and unfair discrimination in AI outputs resulting from biased training data or algorithms.
Chain-of-Thought(CoT)
A prompting technique that encourages AI models to break down complex problems into step-by-step reasoning.
Deep Learning(DL)
A subset of machine learning that uses multi-layered neural networks to learn complex patterns from large amounts of data.
AI Agent
An autonomous AI system that can perceive its environment, make decisions, and take actions to achieve specific goals.
AI Alignment
The challenge of ensuring AI systems behave in accordance with human intentions, values, and goals.
AI Safety
The field focused on preventing AI systems from causing unintended harm and ensuring they remain beneficial.
Application Programming Interface(API)
A set of protocols and tools that allows different software applications to communicate and share data.
Artificial Intelligence(AI)
The simulation of human intelligence processes by computer systems, including learning, reasoning, and self-correction.
Attention Mechanism
A neural network component that allows models to focus on relevant parts of the input when producing outputs.
Autonomous AI
AI systems capable of operating independently, making decisions and taking actions with minimal human oversight.
Batch Normalization(BatchNorm)
A technique that normalizes the inputs of each layer to have zero mean and unit variance, stabilizing and accelerating neural network training.
Benchmark
Standardized tests and datasets used to evaluate and compare AI model performance across different tasks.
Bias in AI
Systematic and unfair discrimination in AI outputs resulting from biased training data or algorithms.
Bidirectional Encoder Representations from Transformers(BERT)
A transformer-based language model that reads text bidirectionally to better understand context and word relationships.
Chain-of-Thought(CoT)
A prompting technique that encourages AI models to break down complex problems into step-by-step reasoning.
Chatbot
A software application designed to simulate conversation with human users through text or voice interfaces.
Chunking
The process of splitting large documents into smaller, manageable pieces for embedding and retrieval in RAG systems.
Classification
A supervised learning task where the model assigns input data to predefined categories or classes.
Clustering
An unsupervised learning technique that groups similar data points together without predefined categories.
Computer Vision(CV)
A field of AI that enables computers to interpret and understand visual information from images and videos.
Constitutional AI(CAI)
An Anthropic-developed approach to training AI systems to be helpful, harmless, and honest using a set of principles rather than extensive human feedback.
Context Length
The maximum number of tokens a language model can process in a single prompt and response combined.
Context Window
The maximum amount of text (measured in tokens) that a language model can process in a single interaction.
Cosine Similarity
A metric that measures the similarity between two vectors by calculating the cosine of the angle between them, commonly used to compare text embeddings.
Deep Learning(DL)
A subset of machine learning that uses multi-layered neural networks to learn complex patterns from large amounts of data.
Diffusion Model
A type of generative model that creates data by learning to reverse a gradual noising process.
Direct Preference Optimization(DPO)
A simpler alternative to RLHF that directly optimizes language models on human preference data without training a separate reward model.
Dropout
A regularization technique that randomly deactivates a percentage of neurons during training to prevent overfitting and improve generalization.
Embeddings
Dense vector representations of data (text, images, etc.) that capture semantic meaning in a numerical format.
Explainability(XAI)
The ability to understand and interpret how an AI model makes its predictions or decisions.
Few-Shot Learning
The ability of AI models to learn new tasks from just a few examples provided in the prompt.
Fine-Tuning
The process of further training a pre-trained model on a specific dataset to adapt it for a particular task or domain.
Foundation Model(FM)
A large AI model trained on broad data that can be adapted to a wide range of downstream tasks.
GPT-Generated Unified Format(GGUF)
A file format for storing quantized large language models optimized for efficient local inference on consumer hardware.
Generative AI(GenAI)
AI systems that can create new content such as text, images, music, code, or video based on learned patterns.
Generative Pre-trained Transformer(GPT)
A family of large language models developed by OpenAI that generate human-like text based on input prompts.
Guardrails
Safety mechanisms and constraints implemented to prevent AI systems from generating harmful, inappropriate, or off-topic content.
Hallucination
When an AI model generates plausible-sounding but factually incorrect or fabricated information.
Image Generation
AI technology that creates new images from text descriptions, sketches, or other inputs.
Inference
The process of using a trained AI model to make predictions or generate outputs from new input data.
LangChain
An open-source framework for building applications powered by large language models, providing tools for chains, agents, and memory.
Large Language Model(LLM)
A type of AI model trained on massive amounts of text data to understand, generate, and manipulate human language.
LlamaIndex
A data framework for connecting custom data sources to large language models, specializing in indexing and retrieval for RAG applications.
Low-Rank Adaptation(LoRA)
A parameter-efficient fine-tuning technique that trains small adapter layers instead of modifying all model weights.
Machine Learning(ML)
A subset of AI that enables systems to automatically learn and improve from experience without being explicitly programmed.
Multimodal AI
AI systems that can process and generate multiple types of data, such as text, images, audio, and video.
Named Entity Recognition(NER)
NLP task that identifies and classifies named entities (people, organizations, locations, etc.) in text.
Natural Language Processing(NLP)
A field of AI focused on enabling computers to understand, interpret, and generate human language.
Neural Network(NN)
A computing system inspired by biological neural networks, consisting of interconnected nodes that process information.
Ollama
An open-source tool that makes it easy to run large language models locally on your computer with a simple command-line interface.
Open Source AI
AI models and tools whose source code and/or weights are freely available for use, modification, and distribution.
Overfitting
When a machine learning model learns the training data too well, including noise and outliers, causing poor performance on new data.
Parameters
The learned weights and biases in a neural network that determine how it processes input and produces output.
Prompt Engineering
The practice of designing and optimizing input prompts to get desired outputs from AI language models.
Prompt Injection
A security attack where malicious input tricks an AI into ignoring its original instructions and following attacker-controlled commands.
Quantization
A technique that reduces model size and increases inference speed by using lower-precision number representations.
Regression
A supervised learning task where the model predicts a continuous numerical value rather than a category.
Regularization
Techniques that prevent overfitting by adding constraints or penalties to the learning process, encouraging simpler models.
Reinforcement Learning(RL)
A type of machine learning where an agent learns to make decisions by receiving rewards or penalties for its actions.
Reinforcement Learning from Human Feedback(RLHF)
A training technique that uses human preferences to fine-tune AI models to be more helpful, harmless, and honest.
Retrieval-Augmented Generation(RAG)
A technique that enhances LLM outputs by retrieving relevant information from external knowledge bases before generating responses.
Semantic Search
Search technology that understands the meaning and context of queries rather than just matching keywords.
Sentiment Analysis
NLP technique that identifies and extracts subjective information, determining whether text expresses positive, negative, or neutral sentiment.
Speech-to-Text(STT)
AI technology that converts spoken audio into written text, also known as automatic speech recognition.
Supervised Learning
A machine learning approach where models learn from labeled training data to make predictions on new, unseen data.
Synthetic Data
Artificially generated data that mimics real-world data, used for training or testing AI models.
System Prompt
Hidden instructions given to an AI model that define its persona, behavior, capabilities, and constraints for a conversation.
Temperature
A parameter that controls the randomness and creativity of AI model outputs during text generation.
Text-to-Speech(TTS)
AI technology that converts written text into natural-sounding spoken audio.
Tokenization
The process of breaking down text into smaller units called tokens that AI models can process.
Tool Use
The capability of AI models to interact with external tools, APIs, and systems to accomplish tasks.
Top-P Sampling
A text generation technique that samples from the smallest set of tokens whose cumulative probability exceeds threshold P.
Transfer Learning
A technique where a model trained on one task is repurposed as the starting point for a model on a different but related task.
Transformer
A neural network architecture that uses self-attention mechanisms to process sequential data, revolutionizing NLP.
Underfitting
When a machine learning model is too simple to capture the underlying patterns in the data, resulting in poor performance on both training and test data.
Unsupervised Learning
A machine learning approach where models discover patterns and structures in unlabeled data without predefined categories.
Vector Database
A specialized database designed to store and efficiently query high-dimensional vector embeddings.
Zero-Shot Learning
The ability of AI models to perform tasks they were not explicitly trained on, without any examples.
AI Moves Fast. Stay Ahead.
New terms added weekly. Subscribe to get updates on the latest AI terminology and discover the AI tools shaping the future.