Track your progress. Sign in locally to save what you finish, keep a streak, and pick up where you left off.
AI Research archive
An interview-first path from math fundamentals to modern LLMs. 6 modules, 22 concise lessons, each with a video, a trusted reading link, and questions worth practising aloud.
Module 1 — Math Foundations for ML
Linear algebra, calculus, and probability & information theory essential for AI and machine learning interviews.
Module 2 — Core ML Theory
Supervised learning, regularization, optimization algorithms, classical ML models, and evaluation metrics.
Module 3 — Deep Learning Theory
Neural network basics, CNNs, sequence models, transformers, and representation embeddings.
Module 4 — Modern LLM Concepts
Pretraining, fine-tuning, PEFT (LoRA/QLoRA), alignment (RLHF/PPO/GRPO/DPO), decoding, and quantization.
Module 5 — Reinforcement Learning
Core RL formulations, MDPs, value functions, Q-learning, DQN, policy gradients, actor-critic, and PPO.
Module 6 — System-Adjacent AI
Production inference, model versioning, A/B testing, drift detection, feature stores, and bias/fairness.