Map of the Field
Introduction
What Is This Guide About?
Each of 38 courses on AI and data is introduced in one presentation. The aim is not to teach these courses but to map them: what question does each one ask, which tools does it share with others, and where does it part ways?
What you will find
- Each course's core question and concepts
- A short history and a typical workflow
- Prerequisites and neighbouring courses
- Overlap and difference tables
- Applications and tools
What you will not find
- Lecture notes or a textbook
- Code examples or assignments
- Derivations of formulas
- The full syllabus of any course
Introduction
Nested Terms: AI ⊃ ML ⊃ ANN ⊃ DL
Each ring is a subfield of the one around it: every deep learning model is a neural network, but not every AI system learns. A chess program that searches is AI, but it is not machine learning.
Structure
Six Parts, 38 Courses
NLP, Reinforcement Learning, Pattern Recognition, Fuzzy Logic, Evolutionary Optimization, Expert Systems, Graphical Models, Generative Models, Multi-Agent Systems, Explainable AI & Ethics
Signal Processing, Image Processing, Computer Vision, Speech and Audio, Medical Imaging, Remote Sensing, Computer Graphics, Robotics, Biometrics
Data Mining, Data Science, Big Data, IR & Recommenders, Time Series, Social Network Analysis
Linear Algebra, Probability & Statistics, Optimization, Information Theory
MLOps, Embedded AI, GPU & Parallel Computing, AI in Cybersecurity, Bioinformatics
Structure
Four Kinds of Relation Between Courses
Deep Learning → Neural Networks
Inherits all of its concepts and adds new ones of its own.
Computer Vision → Image Processing
The other course comes first; this one is built on top of it.
Data Mining ↔ Machine Learning
They use the same tools but ask different questions.
Medical Image Processing → Computer Vision
Applies the other course's methods to one domain, under that domain's rules.
Structure
Criteria for Comparing Courses
The course's reason to exist, in one sentence.
The way of thinking it brings to a problem: search, statistics, logic, transforms…
What kind of data or specification does the course start from?
What comes out at the end: a decision, a model, an image, a report…
How do we tell that a solution is good?
How much mathematics does it rely on, and which kind?
How much data does it need; can it work without data?
Map
Interactive Map
Click a course: its neighbours light up and its relations are listed here.
Map
Links Between Parts
| I | II | III | IV | V | VI | |
|---|---|---|---|---|---|---|
| I. Core | 3 | 13 | 2 | 3 | 8 | 5 |
| II. Branches of AI | 13 | 7 | 9 | 3 | 5 | 2 |
| III. Signals, Images and Audio | 2 | 9 | 10 | 2 | 3 | 3 |
| IV. Data | 3 | 3 | 2 | 5 | 5 | 4 |
| V. Mathematical Foundations | 8 | 5 | 3 | 5 | 2 | · |
| VI. Systems and Applications | 5 | 2 | 3 | 4 | · | 2 |
Map
Hub Courses: The Most Connected
| Course | Links | Some neighbours |
|---|---|---|
| Machine Learning | 15 | Artificial Intelligence, Neural Networks, Linear Algebra, Probability & Statistics … |
| Deep Learning | 9 | Neural Networks, GPU & Parallel Computing, NLP, Reinforcement Learning … |
| Artificial Intelligence | 8 | Machine Learning, Probability & Statistics, Optimization, NLP … |
| Computer Vision | 8 | Image Processing, Deep Learning, Computer Graphics, Pattern Recognition … |
| Data Mining | 8 | NLP, Machine Learning, Big Data, Probability & Statistics … |
| Probability & Statistics | 8 | Artificial Intelligence, Machine Learning, Pattern Recognition, Graphical Models … |
| NLP | 7 | Artificial Intelligence, Deep Learning, IR & Recommenders, Data Mining … |
| Linear Algebra | 7 | Machine Learning, Neural Networks, Computer Graphics, Robotics … |
How to Use
How to Read This Guide
The core courses (Chapters 2–5) are the common language of the whole map; read them first.
Images, language, data or robotics: start from the part that interests you and follow the prerequisite tables backwards.
Open the "Where It Differs" slides of two courses you tend to confuse side by side.
The roadmaps in the last chapter suggest groups of courses that make sense together.