Book 08
AI & Machine Learning
Essential vocabulary for machine learning, large language models and AI-powered applications.
Contents
- 01AGIArtificial General Intelligence1AGI (artificial general intelligence) is a hypothetical AI system that could learn and do any intellectual task a person can, not just a narrow set of tasks.
- 02AI Agent2An AI agent is a system that uses an LLM to plan and carry out multi-step tasks by deciding which tools to call, observing the results, and acting again.
- 03AI Alignment3AI alignment is the field of making AI systems pursue the goals and values their designers intend, so they behave helpfully, honestly, and safely.
- 04Artificial IntelligenceAI4Artificial intelligence (AI) is the field of computer science that builds systems able to do tasks that normally require human intelligence.
- 05Attention Mechanism5The attention mechanism is a neural network technique that lets a model decide, for each token, which other parts of the input matter most and focus on them.
- 06Backpropagation6Backpropagation is the algorithm that trains neural networks by measuring how much each weight added to the error and nudging every weight to reduce it.
- 07Chain-of-Thought Prompting7Chain-of-thought prompting is a technique that asks an LLM to reason through intermediate steps before its final answer, improving accuracy on complex tasks.
- 08Chatbot8A chatbot is a program that converses with people in text or speech, answering questions or helping with tasks, using scripted rules or a language model.
- 09Chunking9Chunking splits long documents into smaller passages before they are embedded and stored, so a RAG system can find and pass on just the relevant parts.
- 10Classification10Classification is the kind of supervised learning where a model predicts a category for each input, such as spam or not spam, or which digit a photo shows.
- 11Computer Vision11Computer vision is the field of AI that enables computers to interpret images and video, such as recognizing objects, reading text, or detecting faces.
- 12Context Engineering12Context engineering is the practice of choosing what an LLM sees on each call (instructions, documents, tool results, history) so it can do the task reliably.
- 13Context Window13A context window is the maximum amount of text, measured in tokens, that an LLM can consider at once, including the prompt, conversation history, and its reply.
- 14Cosine Similarity14Cosine similarity measures how alike two vectors are by the angle between them, from -1 to 1; it is the usual way to compare embeddings in semantic search.
- 15Deep Learning15Deep learning is a subset of machine learning that uses neural networks with many layers to learn complex patterns from raw data such as images and text.
- 16Diffusion Model16A diffusion model is a generative AI model that makes images, audio, or video by starting from random noise and removing it step by step until content appears.
- 17Embedding17An embedding is a list of numbers, called a vector, that represents the meaning of text, images, or other data so that similar items end up close together.
- 18EvalsEvaluations18Evals are tests for AI systems: a set of inputs with expected results or grading rules, run after every change to measure how well a model or prompt performs.
- 19Few-Shot Learning19Few-shot learning is getting an AI model to perform a task from just a handful of examples, most often by placing a few sample inputs and outputs in the prompt.
- 20Fine-tuning20Fine-tuning is the process of taking a pretrained machine learning model and training it further on a smaller, specific dataset to adapt it to one task.
- 21Generative AI21Generative AI is artificial intelligence that creates new content, such as text, images, code, or audio, based on patterns learned from existing data.
- 22GPTGenerative Pre-trained Transformer22GPT (Generative Pre-trained Transformer) is OpenAI's family of large language models that generate text by predicting the next token.
- 23Gradient Descent23Gradient descent is an optimization algorithm that trains machine learning models by repeatedly nudging their parameters in the direction that reduces error.
- 24GuardrailsAI Guardrails24Guardrails are checks placed around an AI model that screen what goes in and what comes out, blocking unsafe, off-topic or malformed requests and answers.
- 25Hallucination25A hallucination is when an AI model, such as an LLM, confidently produces information that sounds plausible but is false, invented, or unsupported by sources.
- 26Inference26Inference is the stage where a trained machine learning model is used to make predictions or generate output from new data, without changing what it learned.
- 27LLMLarge Language Model27An LLM is a machine learning model trained on huge amounts of text that generates language by repeatedly predicting the next most likely piece of text.
- 28LoRALow-Rank Adaptation28LoRA is a cheap way to fine-tune a large model: its weights stay frozen and only small added matrices are trained, so a new skill fits in a few megabytes.
- 29Machine Learning29Machine learning is a branch of artificial intelligence in which computers learn patterns from data to make predictions instead of following hand-written rules.
- 30Mixture of ExpertsMoE30A mixture of experts (MoE) is a neural network design that sends each input to only a few of many small experts, so a huge model costs far less to run.
- 31Model Context Protocol31The Model Context Protocol is an open standard that defines how AI applications connect to external tools, data sources, and prompts through a shared interface.
- 32Model Parameters32Model parameters are the internal numbers, such as weights and biases, that a machine learning model learns in training and uses to turn inputs into outputs.
- 33Multimodal AI33Multimodal AI is artificial intelligence that can understand or generate several types of data, such as text, images, audio, and video, in a single model.
- 34Natural Language Processing34Natural language processing is the field of AI that teaches computers to read, understand, and generate human language in the form of text or speech.
- 35Neural Network35A neural network is a machine learning model made of layers of connected artificial neurons that learn patterns from data by adjusting numeric weights.
- 36Overfitting36Overfitting happens when a machine learning model learns its training data so closely, including its noise, that it performs poorly on new, unseen data.
- 37Prompt37A prompt is the input text or instructions you give an AI model, such as an LLM, to tell it what task to perform and what kind of answer you want.
- 38Prompt Engineering38Prompt engineering is the practice of designing, testing, and refining the instructions given to an AI model so it produces accurate, consistent, useful output.
- 39Quantization39Quantization is a technique that shrinks an AI model by storing its parameters in fewer bits, such as 8 or 4 instead of 16, so inference is faster and cheaper.
- 40RAGRetrieval-Augmented Generation40RAG is a technique that makes an LLM answer using relevant documents retrieved at question time, so its responses are grounded in current, specific data.
- 41Reasoning Model41A reasoning model is a language model trained to work through a problem step by step before answering, spending extra computation to do better on hard tasks.
- 42Regression42Regression is the kind of supervised learning where a model predicts a number, such as a price, a temperature or a delivery time, from the input it is given.
- 43Reinforcement Learning43Reinforcement learning is a type of machine learning in which an agent learns to make decisions by trial and error, earning rewards for good actions.
- 44RLHFReinforcement Learning from Human Feedback44RLHF (reinforcement learning from human feedback) trains a language model to be more helpful and safe using people's judgments of which answers are better.
- 45Semantic Search45Semantic search is a search technique that finds results by meaning rather than exact keywords, usually by comparing embeddings of the query and the documents.
- 46Small Language Model46A small language model (SLM) is a language model with far fewer parameters than the largest LLMs, cheap and fast enough to run on one GPU, a laptop or a phone.
- 47Supervised Learning47Supervised learning is machine learning where a model learns from labeled examples, inputs paired with correct answers, to predict outputs for new data.
- 48System Prompt48A system prompt is the instructions an app gives a language model before the conversation starts, setting its role, rules, tone and what it should know.
- 49Temperature49Temperature is a setting that controls how random an LLM's output is, from focused and predictable at low values to more varied and creative at high values.
- 50Token50A token is the basic unit of text that an LLM reads and generates, usually a whole word, part of a word, or a punctuation mark, mapped to a numeric ID.
- 51Tool Calling51Tool calling is an LLM feature in which the model asks the application to run a specific function with structured arguments, then uses the result in its answer.
- 52TPUTensor Processing Unit52A TPU (Tensor Processing Unit) is Google's custom chip for the matrix math of neural networks, used to train and run AI models, mainly on Google Cloud.
- 53Training Data53Training data is the set of examples a machine learning model learns from, and its quality, size, and coverage largely determine how well the model performs.
- 54Transformer54A transformer is a neural network architecture that uses attention to weigh how each token in a sequence relates to the others, and it powers most modern LLMs.
- 55Underfitting55Underfitting happens when a machine learning model is too simple or too briefly trained to learn the real pattern, so it does poorly even on its training data.
- 56Unsupervised Learning56Unsupervised learning is machine learning in which a model finds patterns, groups, or structure in unlabeled data, without being given the correct answers.
- 57Vector Database57A vector database is a database designed to store embeddings and quickly find the vectors most similar to a query, which powers semantic search and RAG.
- 58Vibe Coding58Vibe coding is building software by describing what you want to an AI and accepting the code it writes, mostly judging the result by whether it seems to work.