Artificial Intelligence

AI systems capable of processing and generating multiple types of data, such as text, images, audio, and video, within a single model. Multimodal models can understand relationships across different m...

An NLP task that identifies and classifies named entities in text into predefined categories such as person names, organizations, locations, dates, and quantities. NER is essential for information ext...

A subfield of AI focused on the interaction between computers and human language. NLP enables machines to read, understand, interpret, and generate human language, powering applications like chatbots,...

An automated machine learning technique that uses algorithms to discover optimal neural network architectures for a given task. NAS explores the design space of layer types, connections, and hyperpara...

A computing system inspired by the biological neural networks of the human brain. Neural networks consist of layers of interconnected nodes (neurons) that process information using weighted connection...

A computer vision task that identifies and locates objects within images or video frames by drawing bounding boxes and assigning class labels. Popular architectures include YOLO, SSD, and Faster R-CNN...

A technology that converts images of text, such as scanned documents, photos, or PDFs, into machine-readable and editable text. Modern OCR uses deep learning to handle diverse fonts, handwriting, and...

A modeling error that occurs when a machine learning model learns the training data too well, including its noise and outliers, resulting in poor performance on unseen data. Overfitting indicates the...

The initial phase of training a foundation model on a large, general-purpose dataset to learn broad representations of language, vision, or other data types. Pre-training captures general knowledge th...

The practice of crafting and optimizing input prompts to guide AI language models toward desired outputs. Prompt engineering involves techniques like few-shot learning, chain-of-thought reasoning, and...

A security vulnerability where malicious input is crafted to manipulate an AI language model into ignoring its instructions, revealing hidden prompts, or performing unintended actions. Prompt injectio...

A model optimization technique that reduces the precision of numerical values used in neural network computations, typically from 32-bit floating point to 16-bit, 8-bit, or even 4-bit representations....

Retrieval-Augmented Generation: a technique that enhances AI language models by retrieving relevant information from external knowledge sources before generating a response. RAG combines the power of...

An AI system that predicts user preferences and suggests relevant items such as products, content, or services. Recommendation systems use collaborative filtering, content-based filtering, or hybrid a...

A class of neural networks designed for sequential data where connections between nodes form directed cycles. RNNs maintain a hidden state that captures information from previous time steps, making th...

A set of techniques used to prevent overfitting by adding constraints or penalties to the model during training. Common methods include L1 (Lasso) and L2 (Ridge) regularization, dropout, early stoppin...

A type of machine learning where an agent learns to make decisions by performing actions in an environment and receiving rewards or penalties. The agent optimizes its strategy (policy) to maximize cum...

A training methodology that uses human preferences to guide the fine-tuning of AI models. RLHF trains a reward model from human comparisons of model outputs, then uses reinforcement learning to optimi...

A framework and set of practices for developing and deploying AI systems that are ethical, transparent, fair, accountable, and respectful of privacy. Responsible AI encompasses governance policies, im...

The interdisciplinary field combining AI, mechanical engineering, and electronics to design, build, and program robots. AI-powered robotics uses computer vision, reinforcement learning, and natural la...