A structured map of artificial intelligence: representations, learning paradigms, model families, and the questions that define the field.
Training seeks a function whose expected loss is small on the data-generating distribution—not only on the examples seen during training.
A reusable technical reading framework for moving from vocabulary to working understanding. Use it alongside the formulas and papers below.
A structured map of artificial intelligence: representations, learning paradigms, model families, and the questions that define the field. Start by naming the representation, objective, and source of evidence in any system you study. This habit separates a useful model explanation from a list of buzzwords.
Use the learning outcomes as checks for understanding: Differentiate symbolic AI, machine learning, deep learning, and foundation models; Choose an appropriate learning setup for a real problem; Reason about data, objectives, generalization, and evaluation. For each claim, ask what assumptions make it true, what data it needs, and how it could fail.
Translate each equation into a small experiment before treating it as memorized knowledge. Expected risk: Training seeks a function whose expected loss is small on the data-generating distribution—not only on the examples seen during training.
Read primary work with a repeatable lens: problem, method, data, measurement, limits, and what would change your mind. This section starts with “Computing Machinery and Intelligence”, “A Logical Calculus of the Ideas Immanent in Nervous Activity”, “Deep Learning”. Follow citations outward only after you can explain the central claim in your own words.
Implement a minimal example using Expected risk; record inputs, outputs, and a failure case.
Define a baseline, a success metric, a stress test, and the evidence required before you trust an improvement.
Choose one paper from the library, reproduce a small claim, then write down the questions its evaluation leaves open.
Primary sources and peer-reviewed work to deepen this page.
Alan M. Turing
Introduces the imitation game and frames machine intelligence as an experimentally testable question.
W. S. McCulloch · W. Pitts
A foundational mathematical model showing how networks of simple units can implement logical computation.
Yann LeCun · Yoshua Bengio · Geoffrey Hinton
A landmark overview of representation learning and the architectures powering modern AI.