learn-ai

Your learning path

Pick how deep you want to go and how much time you have. Depth decides which articles; time decides only how long it takes.

Level
Intermediate
Articles
121
Reading time
157h
Weeks
63

That is 63 weeks at 3h per week. Raising your hours spreads the same material over less time — or drop to a lower target level to study fewer articles.

  1. Week 1

    2h
    1. 1
      What Is Machine Learning?
      ML Foundations 1h
    2. 2
      How Data Becomes Numbers
      ML Foundations 1h

  2. Week 2

    2.3h
    1. 3
      What Is a Neural Network?
      ML Foundations 1.25h
    2. 4
      Weights and Biases
      ML Foundations 1h

  3. Week 3

    3h
    1. 5
      The Forward Pass
      ML Foundations 1h
    2. 6
      Activation Functions
      ML Foundations 1h
    3. 7
      Loss Functions
      ML Foundations 1h

  4. Week 4

    2.6h
    1. 8
      Gradient Descent
      ML Foundations 1.25h
    2. 9
      Backpropagation
      ML Foundations 1.25h

  5. Week 5

    3h
    1. 10
      Overfitting and Generalization
      ML Foundations 1h
    2. 11
      Probability for AI
      ML Foundations 1h
    3. 12
      Train, Validation, Test
      ML Foundations 1h

  6. Week 6

    2.8h
    1. 13
      What Is a Token in AI?
      Foundations 1h
    2. 14
      Classic Text Preprocessing
      Classic NLP 0.75h
    3. 15
      Bag of Words and N-grams
      Classic NLP 1h

  7. Week 7

    2.8h
    1. 16
      What Is an Embedding?
      Foundations 1.5h
    2. 17
      word2vec: Where Word Vectors Began
      Classic NLP 1.25h

  8. Week 8

    2.6h
    1. 18
      Recurrent Neural Networks
      Classic NLP 1.25h
    2. 19
      LSTM and GRU: Memory That Lasts
      Classic NLP 1.25h

  9. Week 9

    2.6h
    1. 20
      Sequence to Sequence and Encoder-Decoder
      Classic NLP 1.25h
    2. 21
      The Origin of Attention
      Classic NLP 1.25h

  10. Week 10

    2.3h
    1. 22
      Where Does the Vocabulary Come From?
      Foundations 1.25h
    2. 23
      What Is an LLM?
      Foundations 1h

  11. Week 11

    2.3h
    1. 24
      How Does an LLM Actually Write?
      Foundations 1.25h Visual explainer
    2. 25
      Base Models vs Chat Models
      Foundations 1h

  12. Week 12

    2.8h
    1. 26
      The Language Modeling Objective
      Foundations 1h
    2. 27
      Logits and Softmax
      Foundations 1h
    3. 28
      Perplexity: A Language Model's Intrinsic Measure
      Foundations 0.75h

  13. Week 13

    2h
    1. 29
      Temperature and Top-p, Explained
      Foundations 1h Visual explainer
    2. 30
      Training vs Inference
      Foundations 1h

  14. Week 14

    2.5h
    1. 31
      What Happens During Pretraining?
      Foundations 1.5h
    2. 32
      What Does "7B Parameters" Mean?
      Foundations 1h

  15. Week 15

    3h
    1. 33
      Decoding Strategies: Greedy Search and Beam Search
      Internals 1h
    2. 34
      The Geometry of Meaning
      Internals 2h Visual explainer

  16. Week 16

    2.5h
    1. 35
      How Does a Transformer Work?
      Internals 2.5h Visual explainer

  17. Week 17

    2.3h
    1. 36
      Encoder, Decoder, and Encoder-Decoder Architectures
      Internals 1.25h
    2. 37
      The Feed-Forward Network in a Transformer
      Internals 1h

  18. Week 18

    2h
    1. 38
      Normalization Layers: LayerNorm and RMSNorm
      Internals 1h
    2. 39
      The Output Projection: From Hidden State to Vocabulary Logits
      Internals 1h

  19. Week 19

    3h
    1. 40
      Self-Attention, Explained Visually
      Internals 3h Visual explainer

  20. Week 20

    2.6h
    1. 41
      Why Transformers Won
      Classic NLP 1.25h
    2. 42
      Why Do AI Models Hallucinate?
      Prompting 1.25h

  21. Week 21

    2.8h
    1. 43
      Prompt Basics
      Prompting 1.25h
    2. 44
      Making a Model Think Step by Step
      Prompting 1.5h Visual explainer

  22. Week 22

    3h
    1. 45
      What Is a Context Window?
      Prompting 1h
    2. 46
      Show, Don't Tell: Few-Shot Prompting
      Prompting 1h
    3. 47
      In-Context Learning: Why Few-Shot Works
      Prompting 1h

  23. Week 23

    2.3h
    1. 48
      Your Prompt Isn't Working. Now What?
      Prompting 1.25h
    2. 49
      Prompt Patterns and Anti-Patterns
      Prompting 1h

  24. Week 24

    2.1h
    1. 50
      Getting JSON Out of an LLM
      Prompting 1.25h
    2. 51
      What Is a System Prompt?
      Prompting 0.75h

  25. Week 25

    3h
    1. 52
      Why RAG Exists
      RAG 1h
    2. 53
      How RAG Works, Step by Step
      RAG 2h Visual explainer

  26. Week 26

    3h
    1. 54
      How to Split Documents for RAG
      RAG 1.5h
    2. 55
      RAG or Fine-Tuning?
      RAG 1.5h

  27. Week 27

    2.6h
    1. 56
      Why You Need a Reranker
      RAG 1.25h
    2. 57
      What Is a Vector Database?
      RAG 1.25h

  28. Week 28

    2.8h
    1. 58
      How Similarity Search Actually Works
      RAG 1.5h Visual explainer
    2. 59
      What Is an AI Agent?
      Agents 1.25h

  29. Week 29

    2h
    1. 60
      How Does Tool Calling Work?
      Agents 2h Visual explainer

  30. Week 30

    2h
    1. 61
      The Agent Loop
      Agents 2h Visual explainer

  31. Week 31

    2.8h
    1. 62
      Agent Architectures: From Rules to Autonomy
      Agents 1.25h
    2. 63
      How Agents Fail
      Agents 1.5h

  32. Week 32

    2.8h
    1. 64
      Writing Good Tool Definitions
      Agents 1.5h
    2. 65
      What Is MCP?
      Agents 1.25h

  33. Week 33

    2.8h
    1. 66
      Multi-Step Planning
      Agents 1.5h
    2. 67
      The ReAct Pattern
      Agents 1.25h

  34. Week 34

    3h
    1. 68
      Your First LLM API Call
      Application 1.5h
    2. 69
      How Do You Know It Works?
      Application 1.5h

  35. Week 35

    1.8h
    1. 70
      From Demo to Production
      Application 1.75h

  36. Week 36

    2.6h
    1. 71
      Which Model Should You Use?
      Application 1.25h
    2. 72
      Cutting Your API Bill
      Application 1.25h

  37. Week 37

    3h
    1. 73
      Why Responses Stream
      Application 1h
    2. 74
      The Bias-Variance Tradeoff
      Evaluation 1h
    3. 75
      Why Evaluation Is Harder Than Training
      Evaluation 1h

  38. Week 38

    2.8h
    1. 76
      Precision, Recall, F1, and Accuracy
      Evaluation 1h
    2. 77
      The Confusion Matrix: Why Accuracy Deceives
      Evaluation 0.75h
    3. 78
      Human Evaluation and Annotation Agreement
      Evaluation 1h

  39. Week 39

    2.3h
    1. 79
      Regression Metrics: MSE, MAE, and R²
      Evaluation 1h
    2. 80
      Retrieval and Ranking Metrics
      Evaluation 1.25h

  40. Week 40

    2h
    1. 81
      ROC and AUC: Evaluation Without a Threshold
      Evaluation 1h
    2. 82
      Text Generation Metrics: BLEU, ROUGE, METEOR
      Evaluation 1h

  41. Week 41

    2h
    1. 83
      How Do Models See Images?
      Multimodal 2h Visual explainer

  42. Week 42

    2h
    1. 84
      How Image Generation Works
      Multimodal 2h Visual explainer

  43. Week 43

    3h
    1. 85
      Multimodal Embeddings
      Multimodal 1.5h
    2. 86
      How Speech Recognition Works
      Multimodal 1.5h

  44. Week 44

    3h
    1. 87
      Vision-Language Models
      Multimodal 1.5h
    2. 88
      Document and OCR Understanding
      Multimodal 1.5h

  45. Week 45

    3h
    1. 89
      How Fine-Tuning Actually Works
      Training and Adaptation 1.5h
    2. 90
      LoRA and Parameter-Efficient Fine-Tuning
      Training and Adaptation 1.5h

  46. Week 46

    2.3h
    1. 91
      Reading Model Benchmarks
      Training and Adaptation 1.25h
    2. 92
      Benchmark Contamination and Goodhart's Law
      Evaluation 1h

  47. Week 47

    1.3h
    1. 93
      Optimizers and Learning Rate
      Training and Adaptation 1.25h

  48. Week 48

    1.8h
    1. 94
      How Models Are Aligned
      Training and Adaptation 1.75h

  49. Week 49

    2.8h
    1. 95
      How Reasoning Models Work
      Training and Adaptation 1.5h
    2. 96
      Transfer Learning: Why Pretraining Reuses
      Training and Adaptation 1.25h

  50. Week 50

    2.8h
    1. 97
      Agentic RAG
      Advanced RAG 1.5h
    2. 98
      Contextual Retrieval
      Advanced RAG 1.25h

  51. Week 51

    3h
    1. 99
      Hybrid Search
      Advanced RAG 1.5h Visual explainer
    2. 100
      RAG over Images and Tables
      Advanced RAG 1.5h

  52. Week 52

    3h
    1. 101
      Query Rewriting and Expansion
      Advanced RAG 1.5h Visual explainer
    2. 102
      Evaluating RAG
      Advanced RAG 1.5h

  53. Week 53

    3h
    1. 103
      Evaluating Agents
      Advanced Agents 1.5h
    2. 104
      Agent Memory
      Advanced Agents 1.5h

  54. Week 54

    3h
    1. 105
      Coding Agents
      Advanced Agents 1.5h
    2. 106
      Context Engineering
      Advanced Agents 1.5h

  55. Week 55

    1.3h
    1. 107
      Human-in-the-Loop Design
      Advanced Agents 1.25h

  56. Week 56

    1.8h
    1. 108
      Multi-Agent Systems
      Advanced Agents 1.75h

  57. Week 57

    3h
    1. 109
      Handling PII and Sensitive Data
      Security 1.5h
    2. 110
      Prompt Injection
      Security 1.5h

  58. Week 58

    2.8h
    1. 111
      Jailbreaks and Guardrails
      Security 1.5h
    2. 112
      Content Moderation
      Security 1.25h

  59. Week 59

    2.8h
    1. 113
      Red-Teaming AI Systems
      Security 1.5h
    2. 114
      Latency Optimization
      Production 1.25h

  60. Week 60

    2.8h
    1. 115
      Observability for LLM Systems
      Production 1.5h
    2. 116
      Cost Monitoring and Attribution
      Production 1.25h

  61. Week 61

    2.3h
    1. 117
      Prompt Versioning
      Production 1h
    2. 118
      A/B Testing AI Features
      Production 1.25h

  62. Week 62

    2.3h
    1. 119
      Statistical Significance: Why One Comparison Deceives
      Evaluation 1h
    2. 120
      Migrating Between Models
      Production 1.25h

  63. Week 63

    1.5h
    1. 121
      Reliability Patterns
      Production 1.5h