Key AI Terminologies

Artificial Intelligence (AI)

Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think and learn like humans. It encompasses various techniques and methodologies to enable machines to perform tasks that typically require human intelligence.

Machine Learning (ML)

Machine Learning (ML) is a subset of AI that focuses on developing algorithms and statistical models that enable computers to perform tasks without explicit programming. It involves the use of data to enable machines to learn patterns and make decisions.

Deep Learning (DL)

Deep Learning (DL) is a subfield of machine learning that involves neural networks with multiple layers (deep neural networks). DL algorithms attempt to mimic the human brain's architecture, allowing systems to learn and make decisions on their own.

Natural Language Processing (NLP)

DL powers language translation services and chatbots, enabling machines to understand and generate human-like text.

Computer Vision

Computer vision is a field of artificial intelligence (AI) that enables computers to interpret, analyze, and understand visual data from the world, such as images and videos. 

Large Language Model (LLM)

A neural network trained to predict the next token in a sequence, enabling natural language understanding and generation

Tokenization

The process of breaking input text into discrete tokens (words or sub-words), crucial for understanding language structure

Vectors

Numerical representations of tokens in an n-dimensional space, where similar meanings cluster closely, enabling semantic understanding

Transformer

A specific architecture for LLMs that processes tokens through multiple stacked attention and feedforward layers to predict the next token.

Few Shot Prompting

Enhancing query responses by providing example inputs during inference to guide the LLM’s output style or content.

Retrieval Augmented Generation (RAG)

Technique combining LLMs with external document retrieval (often from vector databases) to incorporate up-to-date and relevant context into responses.

Vector Database

A specialized database storing embeddings (vectors) for efficient similarity search to find relevant documents matching user queries.

Model Context Protocol (MCP)

A protocol enabling LLMs to access external databases or APIs dynamically to fetch real-time information during query processing.

Chain of Thought

Training strategy encouraging models to reason step-by-step when solving problems, improving the quality and reliability of responses.

AI Agents

Long-running processes integrating LLMs with external systems and tools to autonomously fulfill complex user requests (e.g., travel booking)