A comprehensive, self-paced AI bootcamp curriculum based on the Artificial Intelligence: A Modern Approach (4th Edition) textbook. This roadmap covers the full spectrum of AI, from classical search and logic to modern deep learning, reinforcement learning, and Large Language Model (LLM) agents.
This curriculum is structured into 4 Phases spanning 104 weeks. It balances rigorous theory reading with practical Python implementation, mini-projects, and a capstone system integration.
- Phase I: Foundations and Classical AI Implementation (Weeks 1–26)
- Phase II: Advanced Core AI and Deep Learning Foundation (Weeks 27–52)
- Phase III: Generative AI Specialization (Weeks 53–78)
- Phase IV: Operationalization, Trust, and Agents (Weeks 79–104)
Focus: Agents, Search, Logic, Planning, and Probabilistic Basics
Duration: Weeks 1–26
| Week | Topic |
|---|---|
| 01 | Setup, review, and PEAS |
| 02 | Problem formulation and state spaces |
| 03 | BFS and DFS |
| 04 | Uniform-cost search and weekly wrap |
| 05 | Heuristic functions and greedy search |
| 06 | A* search and optimality |
| 07 | Local search: hill-climbing and simulated annealing |
| 08 | Online search and month-2/3 review |
| 09 | Game trees and minimax |
| 10 | Alpha-beta pruning and simple game agent |
| 11 | CSP modeling and backtracking |
| 12 | CSP heuristics and propagation |
| 13 | Logical agents and propositional basics |
| 14 | Propositional inference and Wumpus world |
| 15 | First-order logic: syntax and semantics |
| 16 | Inference in FOL and unification |
| 17 | Knowledge representation and ontologies |
| 18 | Logic + KR consolidation week |
| 19 | Classical planning and search |
| 20 | Planning graphs and advanced planning |
| 21 | Probability foundations |
| 22 | Conditional independence and BN basics |
| 23 | Exact and approximate inference in BNs |
| 24 | Probabilistic reasoning mini-project and review |
| 25 | Time, state, and temporal models |
| 26 | Smoothing and fixed-interval inference |
Focus: Probabilistic Reasoning, Decision Theory, Machine Learning, and Deep Learning
Duration: Weeks 27–52
| Week | Topic |
|---|---|
| 27 | Viterbi and most likely sequences |
| 28 | Particle filters and temporal review |
| 29 | Probabilistic programming concepts |
| 30 | Decision theory and utilities |
| 31 | Value of information and multiattribute utilities |
| 32 | Decisions review and bridge to MDPs |
| 33 | Markov decision processes (MDPs) |
| 34 | Value iteration and policy iteration |
| 35 | POMDPs and partial observability (conceptual) |
| 36 | Multiagent decision making overview |
| 37 | Learning as a rational activity |
| 38 | Decision trees and evaluation |
| 39 | Linear models and perceptron |
| 40 | Model selection and ensembles |
| 41 | Statistical and Bayesian views of learning |
| 42 | Learning with complete data: Gaussians and mixtures |
| 43 | Learning Bayesian networks |
| 44 | Learning HMMs and chapter review |
| 45 | Feedforward networks and computation graphs |
| 46 | Convolutional networks and regularization |
| 47 | Sequence models (RNNs/LSTMs) |
| 48 | Unsupervised and transfer learning; deep learning review |
| 49 | RL problem formulation and bandits |
| 50 | Value functions and DP backup intuition |
| 51 | Monte Carlo RL |
| 52 | Temporal-difference (TD) learning |
Focus: Reinforcement Learning, NLP, Computer Vision, and Robotics
Duration: Weeks 53–78
| Week | Topic |
|---|---|
| 53 | SARSA and on-policy control |
| 54 | Q-learning and off-policy control |
| 55 | Eligibility traces and n-step methods (optional depth) |
| 56 | Function approximation and deep RL overview |
| 57 | Planning + RL integration |
| 58 | Probabilistic models + RL |
| 59 | Deep RL concept bridge |
| 60 | RL portfolio and pre-capstone planning |
| 61 | Syntax, parsing, and grammars |
| 62 | Semantics and meaning representation |
| 63 | Information extraction and question answering |
| 64 | NLP review and hybridization mini-project |
| 65 | Image formation and basic vision tasks |
| 66 | Recognition and features |
| 67 | Geometry and multi-view vision |
| 68 | Vision review and integrated perception mini-project |
| 69 | Robotics foundations and hardware |
| 70 | Robot planning and RL in robotics |
| 71 | Philosophy, ethics, and safety of AI |
| 72 | Societal impact and capstone positioning |
| 73 | Finalize capstone problem and requirements |
| 74 | High-level architecture and search/planning core |
| 75 | Knowledge representation and constraints |
| 76 | Uncertainty and probabilistic reasoning layer |
| 77 | Decision-theoretic / RL core integration |
| 78 | Supervised/ML components and data strategy |
Focus: Capstone Integration, Deployment, Specialized Research, and Career Prep
Duration: Weeks 79–104
| Week | Topic |
|---|---|
| 79 | NLP interface design (classical + neural) |
| 80 | LLM/tool-use integration |
| 81 | Evaluation framework and experiments |
| 82 | Robustness, safety, and ethics in your system |
| 83 | Documentation, report writing, and visualization |
| 84 | Polish, presentation, and retrospective |
| 85 | Post-capstone audit and gap analysis |
| 86 | Choose specialization and collect resources |
| 87 | Specialization core: literature replication |
| 88 | Specialization extension: add a twist |
| 89 | Portfolio hardening: testing and robustness |
| 90 | Documentation and storytelling |
| 91 | External datasets or APIs integration |
| 92 | Human feedback and interaction loop |
| 93 | Career-oriented packaging: demos and UX |
| 94 | Second opinion and code review |
| 95 | Final knowledge consolidation |
| 96 | Planning what comes after the 24-month bootcamp |
| 97 | Advanced reading and theory deep dive |
| 98 | Open-source AI contribution: orientation |
| 99 | First concrete open-source contribution |
| 100 | Competitive or benchmark project |
| 101 | Teaching and knowledge transfer |
| 102 | Comprehensive self-assessment |
| 103 | Career and portfolio alignment |
| 104 | Long-term roadmap and closing retrospective |
- Languages: Python
- Key Libraries:
aima-python(Official Repo),numpy,scikit-learn,pytorch/tensorflow,opencv,nltk/spacy. - IDE:
VS CodeAntiGravity with Jupyter Notebooks. - Environment: Conda / Virtualenv.
This project is for educational purposes and follows the open-source licenses of the tools and libraries used.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This means:
- ✅ You can share and use this material for educational purposes with proper attribution
- ❌ You may not use it for commercial purposes
- ❌ You may not create derivative works
This repository and its contents are intended for educational and informational purposes only. 📚
All copyrighted material is the property of its respective owners. The use of this content within this repository falls under fair use provisions for purposes such as commentary, education, criticism, and research as outlined in Section 107 of the U.S. Copyright Act of 1976.
If you are the copyright owner and believe that the material has been used improperly, please contact the repository owner to discuss appropriate action.
By using this repository, you acknowledge that the content is not for commercial use and is provided solely to support learning and knowledge-sharing. 🤝
-[Wednesday, December 3, 2025; 10:55:44]: first draft upload -[Thursday, December 5, 2025; 19:13:14]: updated README.md; added aima-python workbook, and "My Study Notes" folder.