Glossary¶
Terms and definitions.
| Term | Definition | Last Updated |
|---|---|---|
| Activation Function | A mathematical function applied to the output of a neuron in a neural network that determines whe... | 2025-08-31 |
| AI Agents | Autonomous artificial intelligence systems designed to perceive their environment, make decisions... | 2025-09-10 |
| AI Alignment | The challenge of ensuring AI systems act in accordance with human values and intentions. As AI be... | 2025-08-31 |
| Algorithm | A set of rules or instructions designed to solve a specific problem or perform a computation. In ... | 2025-08-31 |
| Artificial Intelligence | The simulation of human intelligence in machines that are programmed to think and learn like huma... | 2025-08-31 |
| Artificial Neural Network | A computational model inspired by biological neural networks, consisting of interconnected nodes ... | 2025-08-31 |
| Attention Mechanism | A technique that allows neural networks to focus on specific parts of the input when producing ou... | 2025-08-31 |
| Autoencoder | A type of neural network trained to copy its input to its output through a bottleneck layer. Auto... | 2025-08-31 |
| Autoregressive | A type of model that predicts future values based on previous values in a sequence. In language m... | 2025-08-31 |
| Backpropagation | A supervised learning algorithm used to train neural networks by calculating gradients of the los... | 2025-08-31 |
| Batch Normalization | A technique used in deep neural networks to normalize inputs to each layer, reducing internal cov... | 2025-08-31 |
| BERT | Bidirectional Encoder Representations from Transformers, a pre-trained transformer model that lea... | 2025-08-31 |
| Bias-Variance Tradeoff | A fundamental concept in machine learning describing the tradeoff between bias (error from oversi... | 2025-08-31 |
| Chain-of-Thought Prompting | A prompting technique that encourages language models to generate step-by-step reasoning processe... | 2025-09-10 |
| Classification | A supervised learning task where the goal is to predict discrete categorical labels or classes fo... | 2025-08-31 |
| Clustering | An unsupervised learning technique that groups similar data points together into clusters. The go... | 2025-08-31 |
| Computer Vision | A field of artificial intelligence that enables machines to interpret and analyze visual informat... | 2025-08-31 |
| Constitutional AI | A training approach developed by Anthropic that aims to create AI systems guided by a set of prin... | 2025-09-10 |
| Convolutional Neural Network | A deep learning architecture designed to process grid-like data such as images. CNNs use convolut... | 2025-08-31 |
| Cross-Validation | A resampling technique used to assess how well a machine learning model will generalize to indepe... | 2025-08-31 |
| Deep Learning | A subset of machine learning that uses artificial neural networks with multiple layers to model a... | 2025-08-31 |
| Dimensionality Reduction | The process of reducing the number of features or variables in a dataset while preserving importa... | 2025-08-31 |
| Dropout | A regularization technique used in neural networks to prevent overfitting by randomly setting a f... | 2025-08-31 |
| Feature | An individual measurable property or characteristic of an object being observed. In machine learn... | 2025-08-31 |
| Feature Engineering | The process of selecting, modifying, or creating features from raw data to improve machine learni... | 2025-08-31 |
| Few-Shot Learning | A machine learning approach where models learn to perform tasks with only a few examples. In the ... | 2025-08-31 |
| Fine-tuning | The process of adapting a pre-trained model to a specific task or domain by continuing training o... | 2025-08-31 |
| Foundation Models | Large-scale AI models trained on broad, diverse datasets that serve as a foundation for a wide ra... | 2025-09-10 |
| Gated Recurrent Unit | A simplified variant of LSTM that uses gating mechanisms to control information flow in recurrent... | 2025-08-31 |
| Generalization | The ability of a machine learning model to perform well on new, unseen data that was not part of ... | 2025-08-31 |
| Generative Adversarial Network | A deep learning architecture consisting of two neural networks competing against each other: a ge... | 2025-08-31 |
| GPT | Generative Pre-trained Transformer, a family of autoregressive language models that generate text... | 2025-08-31 |
| Gradient Descent | An optimization algorithm used to minimize loss functions by iteratively moving in the direction ... | 2025-08-31 |
| Image Classification | A computer vision task where algorithms assign category labels to entire images. The goal is to d... | 2025-08-31 |
| In-Context Learning | The ability of language models to learn and adapt to new tasks during inference by using examples... | 2025-08-31 |
| Inference | The process of using a trained machine learning model to make predictions or decisions on new, un... | 2025-08-31 |
| Large Language Model | A type of artificial intelligence model that has been trained on vast amounts of text data to und... | 2024-08-28 |
| Long Short-Term Memory | A type of recurrent neural network architecture that can learn long-term dependencies in sequenti... | 2025-08-31 |
| Machine Learning | A subset of artificial intelligence that enables computers to learn and improve from experience w... | 2025-08-31 |
| Masked Language Model | A training objective where random tokens in a sequence are masked (hidden) and the model learns t... | 2025-08-31 |
| Mixture of Experts (MoE) | A neural network architecture that uses multiple specialized sub-networks (experts) along with a ... | 2025-09-10 |
| Model | A mathematical representation of a real-world process, created by training an algorithm on data. ... | 2025-08-31 |
| Multi-Head Attention | An extension of self-attention that runs multiple attention mechanisms in parallel, each focusing... | 2025-08-31 |
| Multilayer Perceptron | A feedforward artificial neural network with multiple layers of nodes between input and output la... | 2025-08-31 |
| Multimodal Models | AI models capable of processing, understanding, and generating content across multiple modalities... | 2025-09-10 |
| Natural Language Processing | A branch of artificial intelligence that focuses on the interaction between computers and human l... | 2025-08-31 |
| Neural Network | A computing system inspired by biological neural networks. It consists of interconnected nodes (n... | 2025-08-31 |
| Object Detection | A computer vision task that involves identifying and localizing objects within images or videos. ... | 2025-08-31 |
| Overfitting | A modeling error that occurs when a machine learning model learns the training data too well, inc... | 2025-08-31 |
| Perceptron | A single-layer neural network that is the simplest type of artificial neural network. It consists... | 2025-08-31 |
| Pre-training | The initial training phase where a model learns general patterns from large amounts of unlabeled ... | 2025-08-31 |
| Prompt | Input text or instructions given to a language model to guide its output generation. Effective pr... | 2025-08-31 |
| Prompt Engineering | The practice of designing and optimizing prompts to effectively communicate with language models ... | 2025-08-31 |
| Recurrent Neural Network | A type of neural network designed to process sequential data by maintaining internal memory throu... | 2025-08-31 |
| Regression | A supervised learning task where the goal is to predict continuous numerical values for given inp... | 2025-08-31 |
| Reinforcement Learning | A type of machine learning where an agent learns to make decisions by taking actions in an enviro... | 2025-08-31 |
| Reinforcement Learning from Human Feedback (RLHF) | A training methodology that uses human preferences to fine-tune language models and other AI syst... | 2025-09-10 |
| ReLU | Rectified Linear Unit, an activation function that outputs the input directly if positive, otherw... | 2025-08-31 |
| Retrieval-Augmented Generation (RAG) | A framework that enhances language models by combining parametric knowledge stored in model weigh... | 2025-09-10 |
| Self-Attention | An attention mechanism where each element in a sequence attends to all elements in the same seque... | 2025-08-31 |
| Semantic Segmentation | A computer vision task that assigns a class label to every pixel in an image, creating pixel-leve... | 2025-08-31 |
| Supervised Learning | A type of machine learning where algorithms learn from labeled training data to make predictions ... | 2025-08-31 |
| Test-Time Compute | A scaling paradigm that improves AI model performance by allocating additional computational reso... | 2025-09-10 |
| Tokenization | The process of breaking down text into smaller units called tokens, such as words, subwords, or c... | 2025-08-31 |
| Tool Use (Function Calling) | The ability of AI models, particularly language models, to interact with external tools, APIs, an... | 2025-09-10 |
| Training Data | The dataset used to teach a machine learning algorithm. It consists of input examples and their c... | 2025-08-31 |
| Transformer | A neural network architecture that relies entirely on attention mechanisms to process sequential ... | 2025-08-31 |
| Underfitting | A modeling error that occurs when a machine learning model is too simple to capture the underlyin... | 2025-08-31 |
| Unsupervised Learning | A type of machine learning that finds patterns in data without labeled examples. The algorithm di... | 2025-08-31 |
| Variational Autoencoder | A type of autoencoder that learns a probabilistic latent representation of data. VAEs can generat... | 2025-08-31 |
| Zero-Shot Learning | A learning paradigm where models perform tasks without having seen specific examples during train... | 2025-08-31 |
71 terms