Curriculum Catalog

Python Programming: Beginner to Job‑Ready Learn Python from scratch with hands-on practice, mini projects, and interview-focused problem solving. Perfect for beginners.

Learn to think like a computer scientist before writing a single line of code.

Master the data structures and algorithms every AI and ML engineer must know.

The math every AI learner needs — from algebra to trigonometry, built for AI applications.

Master probability — from Bayes' theorem to the distributions that power ML models.

Descriptive stats, hypothesis testing, A/B testing, and regression — built for Data Scientists.

Vectors, matrices, eigenvalues, and PCA — the linear algebra powering every AI model.

Derivatives, gradients, and gradient descent — the calculus that trains neural networks.

SQL, relational databases, normalization, and intro to NoSQL — for data and AI engineers.

EDA, data cleaning, visualization, and storytelling — applied to real datasets.

The "why" of ML — theory, taxonomy, generalization, bias-variance, and the ML workflow.

Linear, Ridge, Lasso, and Logistic Regression — implemented from scratch with math.

k-NN, Naive Bayes, Decision Trees, Random Forest, and SVM — with theory and code.

K-Means, DBSCAN, PCA, and anomaly detection — finding patterns in unlabeled data.

XGBoost, LightGBM, stacking, SHAP, and feature engineering — advanced ML for practitioners.

Cross-validation, ROC-AUC, data leakage, hyperparameter tuning — real ML evaluation.

BFS, DFS, A*, minimax, and CSPs — the classical AI algorithms every AI engineer must know.

Logic, inference, knowledge graphs, and expert systems — classical AI reasoning.

Q-learning, policy gradients, and deep RL — teach AI to learn from interaction.

Build a neural network in pure Python — perceptrons, backprop, and gradient descent from scratch.

Deep learning with PyTorch — MLP, CNN, RNN, LSTM, attention, and transfer learning.

Image classification, object detection, segmentation, YOLO, and Vision Transformers.

Text representation, Word2Vec, sequence models, and attention — foundations of modern NLP.

Build a Transformer from scratch — attention, positional encoding, and autoregressive generation.

Pretraining, scaling, RLHF, and inference — how large language models actually work.

Build with LLMs: RAG, embeddings, vector databases, function calling, and hallucination mitigation.

LoRA, QLoRA, instruction tuning, quantization, and distillation — adapt LLMs for your use case.

Vision-language models, speech, video, and multimodal agents — AI that sees, hears, and talks.

APIs, model serving, caching, observability, and cost optimization — production AI backends.

Docker, CI/CD, model registry, monitoring, and GPU inference — MLOps in production.

Red teaming, prompt injection, adversarial attacks, guardrails, and responsible AI.

Agent fundamentals: perception, reasoning, planning, memory, tools, and feedback loops.

Production agentic systems: multi-agent orchestration, reliability, observability, and security.

From customer problem to deployed AI product — the Forward Deployed Engineer skillset.

Read papers, design experiments, run ablations, and write technical reports like a researcher.

Build a complete AI system: recommendation engine, autonomous agent, RAG app, or AI product.