The roadmap
From dot products to autonomous agents.
Seven branches, ordered by dependency. Each concept is one sentence you can expand — tick it off once you could explain it to someone else. Progress stays in your browser.
- 7
- branches
- 593
- concepts
- 555
- articles live
- 90.4h
- total reading
● Branch 01
Mathematics
The five languages every model and every analysis is written in.
0/26 known
2.5 h total
1.1Linear Algebra
1.2Calculus & Optimization
1.3Probability
1.4Statistics
1.5Information Theory
● Branch 02
ML Algorithms
Classical models — small, fast, and still everywhere.
0/68 known
6.9 h total
2.1Supervised · Regression
2.2Supervised · Classification
2.3Unsupervised · Clustering
2.4Unsupervised · Dimensionality Reduction
2.5Unsupervised · Association Rule Learning
2.6Unsupervised · Anomaly Detection
2.7Evaluation & Generalization
● Branch 03
Deep Learning
Differentiable programs trained end to end.
0/376 known
67.4 h total
3.1Deep Learning Fundamentals
3.2Activation Functions
3.3Neural Network Algorithms
3.4Loss Functions
3.5Optimization Algorithms
3.6Regularization & Normalization
3.7Convolutional Neural Networks
3.8Recurrent Neural Networks and Sequence Models
3.9Attention and Transformer Architectures
3.10Generative Deep Learning Algorithms
3.11Large Language Models (LLMs)
3.12Deep Learning for NLP
3.13Deep Learning for Computer Vision
3.14Speech and Audio Deep Learning
3.15Graph Neural Networks (GNNs)
3.16Architectures
● Branch 04
Reinforcement Learning
Learning to act from reward alone, by trial and error.
0/16 known
1.4 h total
4.1Foundations
4.2Tabular Methods
4.3Deep RL
4.4Beyond the Basics
● Branch 05
Generative AI
Models that produce text, images, and more.
0/85 known
11.0 h total
5.1Foundations of Generative AI
5.2Prompt Engineering
5.3Decoding and Generation Control
5.4Retrieval-Augmented Generation (RAG)
5.5Multimodal Generative AI
5.6Customization
5.7Evaluation of Generative Models
5.8Safety, Alignment and Responsible AI
5.9Serving Generative Models
5.10Applications
● Branch 06
Agentic AI
Models that act — call tools, plan, and loop.
0/13 known
0.8 h total
6.1LLM Agents
6.2Memory & Context
6.3Planning & Orchestration
6.4Reliability
● Branch 07
MLOps & Systems
Getting models out of notebooks and into production.
0/9 known
0.6 h total
7.1Data & Experiments
7.2Deployment & Inference
7.3Monitoring & Scale