Artificial Intelligence

Computer Vision

This guide helps you get your bearings in Computer Vision before you start exploring the interactive timeline, framework graph, and concept maps.

Before You Dive In

Computer Vision sits inside AI's central problem: building systems that perceive, reason, and act under uncertainty.
Rough timeline: symbolic AI and search -> probabilistic methods -> statistical learning -> deep learning and foundation-model era.
Start with the symbolic vs statistical debate; modern systems often combine both rather than choosing one.
Use Noosaga to compare frameworks by capability focus: perception, reasoning, planning, interaction, or control.

SearchAlgorithmic exploration of state spaces to find solutions under constraints.

Probabilistic inferenceReasoning with uncertainty using probabilities and conditional dependence.

Representation learningLearning useful features directly from data instead of hand-crafting them.

TransformerAttention-based architecture behind most modern large language and multimodal models.

AlignmentMethods for making AI objectives and behavior match human goals and constraints.

Treating AI as one monolithic method; the field contains multiple competing frameworks and hybrids.

Assuming larger models always solve reasoning reliably; scaling helps, but task structure and evaluation still matter.

Confusing benchmark gains with robust real-world generalization.

Open the interactive view and scan the framework timeline. Which frameworks came first? Which ones overlap? Where are the big transitions?

Click into individual frameworks to read what each one claims, where it came from, and how it relates to its neighbors.

See how the key ideas within a framework connect. This is useful for figuring out what to learn first and what depends on what.

Take the quiz for any framework you've read about. It's a quick way to find out whether you actually understood the core ideas or just skimmed them.