← Back to CoursesArtificial Intelligence: Advanced

Neuroanatomy Explorer

Drag to rotate · scroll to zoom · click regions to explore

View
Loading 3D model…

Click a region
to explore it

Memory Deck

Flip each card and rate whether you knew it. Your score is saved.

Term
Definition

Deck complete — score saved.

Match the Pairs

Match each term to its definition. Finish the board to earn your score.

All matched — score saved.

Concept Constellation

Every key idea in this course, mapped as an explorable 3D constellation. Drag to rotate, scroll to zoom, click a node.

Click a node to read its definition.

Foundations of Modern Artificial Intelligence

Manual: General · Subject: Artificial Intelligence

Survey the historical, mathematical, and conceptual foundations that underpin advanced AI systems.

What Counts as AI?

Definition and scope

Artificial Intelligence (AI) studies agents that perceive, reason, learn, and act under uncertainty to achieve goals. Modern AI spans symbolic reasoning, machine learning, probabilistic inference, optimization, and systems that combine these paradigms.

🔑

Core idea

AI is less a single algorithm than a design space of representations, search procedures, learning rules, and decision-making frameworks.

Historical milestones

Selected milestones

EraContribution
1950sTuring test, early symbolic reasoning
1980sExpert systems and probabilistic AI
1990sStatistical learning and graphical models
2010sDeep learning at scale
2020sFoundation models and large-scale multimodal systems

Paradigm shifts

Early AI emphasized explicit rules and search. Statistical AI introduced uncertainty-aware models and generalization from data. Deep learning added hierarchical representation learning, while recent foundation models exploit self-supervised pretraining and large-scale transfer.

Which statement best distinguishes statistical AI from classical symbolic AI?

In one sentence, what is an agent in AI?

Core mathematical tools

Math toolkit

Linear algebra
Vectors, matrices, eigenvalues, singular value decomposition, and embeddings
Probability
Random variables, conditional independence, Bayesian inference
Optimization
Loss minimization, gradients, constrained and stochastic optimization
Information theory
Entropy, cross-entropy, mutual information

Why is optimization central to modern AI?

💡

Study strategy

When studying AI theory, separate representation, inference, learning, and decision-making. Most advanced systems combine all four.