Skip to content

Jeff Liu's AI Learning Notes

Welcome! This is a comprehensive collection of AI learning notes covering computer science, machine learning, deep learning, reinforcement learning, AI engineering, and more. The content is drawn from coursework, classic textbooks, online resources, and hands-on practice.


  • Logs

    AI learning diary, project notes (Alice Project — generative agent world simulation)

    Enter →

  • Computing Science

    Computer science, algorithms & data structures, mathematical foundations (calculus, linear algebra, probability, information theory, statistics, automatic differentiation)

    Enter →

  • Symbolicism

    AIMA (search, logic, knowledge representation, Bayesian networks, decision theory), AI Planning (classical planning & decision-making, motion planning & trajectory optimization)

    Enter →

  • Machine Learning

    ML fundamentals, data science (EDA, feature engineering), classical supervised learning (SVM, Random Forest, XGBoost, LightGBM)

    Enter →

  • Deep Learning

    CNN, RNN/LSTM, Transformer, generative models (VAE/GAN/Diffusion), foundation models, optimization & regularization

    Enter →

  • Reinforcement Learning

    Classical RL (MDP/TD/Policy Gradient), Deep RL (DQN/PPO/SAC), Offline RL, MBRL, LLM post-training

    Enter →

  • AI Agents

    AI Agent architectures, reasoning patterns (ReAct/CoT/ToT), generative agents

    Enter →

  • Robotics

    Robotics overview, simulation & hardware platforms, embodied intelligence, intuitive physics

    Enter →

  • Human-Like Intelligence

    Philosophy of mind, neuroscience insights, world models (JEPA), causal reasoning, meta-learning

    Enter →

  • Brain-Computer Interface

    Neurophysiology, intention-to-action pipeline, neural foundation models, brain-to-language/image decoding, sensory writing, commercial/clinical & neurorights

    Enter →

  • AI Engineering

    PyTorch development, data engineering, fine-tuning, inference deployment (vLLM), MLOps, AI infrastructure

    Enter →

  • AI Safety & Trustworthiness

    Adversarial attacks & defenses, LLM jailbreaking, red teaming, explainability, robustness, privacy protection

    Enter →


Other notes: Finance Learning Notes →


Images in these notes are sourced from the internet, public courseware, and textbooks. Please contact for removal if any copyright is infringed.


评论 #