Algorithm
A sequence of rules or steps designed to perform a specific task or solve a problem. In AI, algorithms help computers learn patterns from data.
Artificial Intelligence (AI)
The simulation of human intelligence in machines — enabling them to learn, reason, and make decisions.
Machine Learning (ML)
A subset of AI that allows systems to automatically learn and improve from experience without explicit programming.
Neural Network
A model inspired by the human brain, consisting of interconnected nodes (“neurons”) that process information and learn patterns.
Deep Learning
A subset of machine learning using multi-layered neural networks to model complex patterns in large datasets.
Natural Language Processing (NLP)
The branch of AI focused on enabling computers to understand, interpret, and generate human language.
Computer Vision
AI technology that allows computers to interpret and understand visual information from the world, like images and videos.
Reinforcement Learning
A type of machine learning where an agent learns to make decisions by performing actions and receiving rewards or penalties.
Dataset
A collection of data used to train, validate, and test AI and ML models.
Bias
Unintended or unfair tendencies in an AI system that arise from biased data or model assumptions.
Overfitting
When a model learns the training data too well, including noise, and performs poorly on unseen data.
Underfitting
When a model is too simple to capture the underlying patterns in data, leading to poor accuracy.
Supervised Learning
A type of machine learning where the model is trained on labeled data (with known outputs).
Unsupervised Learning
Learning from unlabeled data to find hidden patterns or groupings without explicit guidance.
Generative AI
AI systems capable of creating new content, such as text, images, or music — e.g., ChatGPT, DALL·E.
Prompt Engineering
The process of crafting inputs (prompts) to guide AI models like ChatGPT toward desired responses.
Token
A unit of text (word, subword, or symbol) that AI models process when generating or analyzing language.
API (Application Programming Interface)
A set of rules that allows software applications to communicate and interact with each other — often used to access AI models.
Model Training
The process of teaching a machine learning model using data, so it can make predictions or decisions.
Inference
The phase where a trained model makes predictions on new, unseen data.
LLM (Large Language Model)
A massive AI model trained on vast text data to understand and generate human-like text, e.g., GPT-4, Claude, Gemini.
Transformer
An AI model architecture that uses self-attention mechanisms, powering most modern language models.
Embedding
A numeric representation of text, image, or other data, allowing AI systems to compare similarities and meanings.
AI Ethics
The study and practice of developing AI responsibly, ensuring fairness, transparency, and accountability.
Chatbot
An AI application designed to simulate conversation and assist users through text or voice interfaces.
Fine-Tuning
Adjusting a pre-trained model using specific data to improve its performance on a narrower task.
Data Labeling
The process of tagging or categorizing raw data so it can be used for supervised learning.
Zero-Shot Learning
When an AI model performs tasks it was never explicitly trained for, based on general understanding.
Few-Shot Learning
Training a model to perform well with only a few examples or data samples.
Hallucination (AI)
When a generative AI produces false or fabricated information that appears plausible.
AI Agent
An autonomous system that perceives its environment and acts upon it to achieve specific goals.
Computer Vision
AI systems designed to interpret and understand visual input like images and videos.
Data Preprocessing
Cleaning and organizing raw data before training models to improve accuracy and efficiency.
Ethical AI
Developing and deploying AI systems that prioritize fairness, privacy, and human-centered values.