💡 AI (Artificial Intelligence)

AI (Artificial Intelligence)#

Systems that perform tasks normally requiring human intelligence.

Important

✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.

What it is#

Artificial intelligence (AI) is the broad field of computer science aimed at building systems that perform tasks that normally require human intelligence — reasoning, learning, problem-solving, perception, language and decision-making. It is the umbrella term beneath which Machine Learning, Deep Learning and other methods sit.

Core capabilities#

AI systems aim at a handful of capabilities: learning from data or experience (ML, DL); reasoning to logical decisions (symbolic AI, expert systems); perception of the world (vision, speech); language understanding (NLP, large language models); and action/autonomy (robotics, self-driving cars, agents).

Narrow, general, super#

Today’s systems are narrow (weak) AI — focused on one task (spam filters, recommenders, voice assistants, chatbots). General AI (AGI) — human-level competence across arbitrary tasks — remains hypothetical and unachieved, and superintelligence, surpassing humans in every domain, is a theoretical further step.

AI vs ML vs DL, and the trade-offs#

The nesting is the key relationship: AI is the broad goal, machine learning is the subset that learns from data, and deep learning is the subset of ML built on neural networks for complex perception and language. The field automates tasks, augments decision-making and unlocks insight from large data — across healthcare, finance, transport and generative tools — but carries real challenges: bias and fairness, the interpretability of black-box models, the energy and cost of training, and safety, regulation and ethics.

Theme: AI & ML Concepts · All terminology

Hint

Mind map — connected ideas

Machine Learning (ML) · Neural Networks · Bayesian Neural Networks (BNNs) · Variational Inference (VI) · Model Distillation (Knowledge Distillation) · Quantization

Hint

More in AI & ML Concepts

Classification Models · Computer Vision (CV) · Decision Trees · Linear Models · LLMs (Large Language Models) · Logistic Regression · Machine Learning (ML) · Medical AI · Natural Language Processing (NLP) · Neural Networks · Regression Models · Support Vector Machines (SVMs) · Target Variable