LearnAI

Navigation

Introduction to AI

Machine Learning

Deep Learning

NLP & LLMs

Computer Vision

Generative AI

Reinforcement Learning

AI Ethics & Governance

Tools & Frameworks

General

Branches of Artificial Intelligence - Mapping the Field's Major Subareas

“Artificial intelligence” is an umbrella term covering many distinct subfields, each with its own methods, goals, and history. Understanding how they relate helps make sense of where specific techniques (like deep learning) fit into the broader picture.

Artificial Intelligence
├── Symbolic AI / Knowledge Representation and Reasoning
├── Machine Learning
│   └── Deep Learning
├── Natural Language Processing
├── Computer Vision
├── Robotics
├── Planning and Search
└── Multi-Agent Systems

Symbolic AI

The earliest branch, symbolic AI represents knowledge as explicit rules, facts, and logical relationships, and reasons over them using formal inference. Expert systems and knowledge graphs are direct descendants of this approach. It excels at problems with clear, well-defined rules but struggles with ambiguity and the need to learn from raw, unstructured data.

Machine Learning and Deep Learning

Machine learning replaces hand-written rules with statistical patterns learned from data. Deep learning is a subfield of machine learning that uses multi-layer neural networks, and it has become the dominant approach for perception-heavy tasks like vision and language, since it can automatically learn useful features rather than requiring them to be hand-engineered.

Natural Language Processing

NLP focuses specifically on understanding and generating human language—from classic tasks like part-of-speech tagging and parsing to modern large language models that handle translation, summarization, and open-ended conversation.

Computer Vision

Computer vision gives machines the ability to interpret visual information from images and video: recognizing objects, tracking motion, reconstructing 3D scenes, and more. It overlaps heavily with deep learning today but has its own specialized architectures and evaluation methods.

Robotics

Robotics combines AI with physical embodiment—perception, planning, and control must work together in real time, under uncertainty, with real physical consequences for mistakes. It draws on control theory and reinforcement learning as much as on perception models.

This branch studies how to find a sequence of actions that achieves a goal, from classical algorithms like A* search to modern planning systems used in logistics, game AI, and robotics task planning.

Multi-Agent Systems

Multi-agent systems study how multiple AI agents (or an AI agent and humans) interact, cooperate, or compete—relevant to negotiation, game theory-based AI, swarm robotics, and increasingly, teams of large language model agents coordinating on complex tasks.

These branches are not strictly separate in practice—modern systems often combine several, such as a robot that uses computer vision for perception, reinforcement learning for control, and a language model for high-level task instructions.