AI Landscape

Four pillars from classical ML to autonomous agents.

Learns patterns from data to make predictions and decisions.

Supervised Learning Train models with labeled examples.

Unsupervised Learning Find structure in unlabeled data.

Reinforcement Learning Learn by reward through interaction.

Uses neural networks with many layers to learn complex representations.

Neural Networks Building blocks of deep learning.

CNN Convolutional nets for vision and spatial data.

RNN Recurrent nets for sequences.

Transformers Attention-based architectures powering modern AI.

Creates new content — text, images, audio, and more.

LLMs Large language models for text understanding and generation.

Multimodal Models Models that combine text, image, audio, and video.

Diffusion Models Generative models for high-quality images and media.

Foundation Models Large pretrained models adapted to many tasks.

Autonomous systems that plan, act, remember, and use tools.

Plans Goal decomposition and planning loops.

Act Taking actions in tools and environments.

Memory Short and long-term agent memory.

Tools APIs, retrieval, and external capabilities.