A full map of everything in this repo, organized the way it's built: Courses are assembled
from Workshops, which are assembled from Seminars (see the README for what each tier means).
Every driver below is a .tex file in LaTeX/: open it directly, or compile it with texify
(see the README's Getting Started section).
Where a seminar is only reachable as part of a workshop (it has no standalone driver of its own), it's listed as plain text rather than a link.
Driver: Main_Course_MachineLearning_Presentation.tex
- Python for ML: Intro, Constructs, Procedures, OOP, IO & Libraries, Closures
- Foundations: Intro, Data Prep
- Regression: Regression
- Tree-Based & Ensemble: Decision Trees, Ensemble
- Supervised II: KNN, SVM & Naive Bayes
- Unsupervised & Deployment: Clustering, Dimensionality Reduction, Deployment
There's also a standalone bundle of just the 5 ML-specific workshops (no Python, no demos):
Main_Workshop_MachineLearning_Presentation.tex.
Driver: Main_Course_Python_Presentation.tex
- Basic Python: same 6 seminars as above (Intro, Constructs, Procedures, OOP, IO & Libraries, Closures)
- Advanced Python: OOP & Iteration, Functions & OS, Strings & Web, Data Libraries, Visualization, Problems
Driver: Main_Course_MathsML_Presentation.tex
- Basics: Numbers & Equations, Sets & Proofs
- Linear Algebra: Vectors, Matrices
- Calculus: Functions & Limits, Derivatives & Optimization
- Statistics: Probability Foundations, Random Distributions, Central Tendency & Spread, Distributions & Expected Value, Hypothesis Testing, Tests in Practice
Driver: Main_Course_DeepLearning_Presentation.tex
- Deep Learning Workshop: Foundations (workshop-only), TensorFlow core (workshop-only), PyTorch
- Course-specific extras (no dedicated workshop): AI/tech intro, Python syntax primer, self-organizing maps, autoencoders
Driver: Main_Course_GenerativeAI_Presentation.tex
- Natural Language Processing: NLP basics, POS & NER (both workshop-only), NLP + ML, NLP advanced (workshop-only)
- Deep NLP: word embeddings, word2vec, text generation (topic files, not a seminar chain)
- LLMs: Intro, Transformers, ChatGPT From Zero (Short) (workshop-only), Evaluation, Prompt Engineering, Fine-Tuning, RAG, Agents, Production, Reasoning, LangChain, LlamaIndex, LLM applications (workshop-only)
- Course-specific extras: ChatGPT applications (BDO/IMI/HR/journalism), advanced RAG, LangGraph deep-dive
All-in-one driver: Main_Course_MLCoEP_Presentation.tex
A bespoke 20-session course built for College of Engineering Pune (CoEP), pairing Python/ML fundamentals with mechanical-engineering-flavored applications and project ideas. Unlike the 5 courses above, it has no separate workshop layer; all 20 sessions are chained directly into the single all-in-one course driver above: AI Overview, Python Overview, EDA & Data Preparation, Pandas, Introduction to ML, Core ML Concepts, ML Workflow & Model Evaluation, Feature Selection, Linear Regression, Logistic Regression, Decision Trees, Ensemble Methods & Random Forest, SVM, Naive Bayes, KNN, K-Means, PCA, Titanic Capstone, MLOps & Deployment, and AI/ML Applications & Project Ideas for ME.
These aren't part of any of the 5 courses above: each is a complete, independent session.
| Workshop | Driver | Covers |
|---|---|---|
| AI (broad survey) | Main_Workshop_AI_Presentation.tex |
Python → AI → Data Analytics → ML → DL → NLP → Word Embeddings → LLM Intro → Agents → Career in Data Science, all via existing standalone seminars |
| RAG (core) | Main_Workshop_LLM_RAG_Presentation.tex |
RAG, LangChain, Evaluation, advanced RAG (workshop-only) |
| RAG to Riches | Main_Workshop_RAGToRiches_Presentation.tex |
End-to-end journey: Python → ML → NLP → Word Embeddings → RAG → Docling → LangChain → Evaluation |
| RAG2Riches (bootcamp) | Main_Workshop_LLM_RAG2Riches_Presentation.tex |
A full 3-week (or 12-week part-time) day-by-day bootcamp curriculum: Python → DSA → System Design → NLP → ML → LLMs → RAG → Production, with daily projects and a capstone |
| LLM Agents | Main_Workshop_LLM_Agents_Presentation.tex |
Agent concepts, MCP, eval, Agents seminar |
| Document Parsing (Docling) | Main_Workshop_LLM_Docling_Presentation.tex |
Docling architecture, multimodal parsing, resume parsing, production/evals |
| LangChain | Main_Workshop_LLM_LangChain_Presentation.tex |
Framework, implementation, what's new |
| LangGraph | Main_Workshop_LLM_LangGraph_Presentation.tex |
Intro, advanced, implementation |
| Transformers | Main_Workshop_LLM_Transformers_Presentation.tex |
History (through word2vec, seq2seq/attention) → architecture → pretraining → BERT → HuggingFace → applications |
| Graph Databases | Main_Workshop_Graph_Database_Presentation.tex |
Graph basics, Neo4j, graph data science (full workshop versions) |
| Geometric Deep Learning | Main_Workshop_Graph_GeometricDeepLearning_Presentation.tex |
GDL, GNNs, PyTorch Geometric, knowledge graphs, category theory (workshop-only) |
| Knowledge Graphs | Main_Workshop_Graph_KnowledgeGraph_Presentation.tex |
Graph algorithms, KG semantics, KG + LLMs, implementations |
| Chatbots (Rasa) | Main_Workshop_NLP_Chatbot_Rasa_Presentation.tex |
Chatbot design, Rasa install/concepts/theory, slots/forms/deployment, a full IPL-bot walkthrough |
| spaCy | Main_Workshop_NLP_SpaCy_Presentation.tex |
Pipelines, POS/NER, classification, med7 |
| Data Analytics | Main_Workshop_Data_Analytics_Presentation.tex |
Data concepts, dimensionality, pandas, prep, exploration, visualization, with demo/assignment case studies |
| Reinforcement Learning | Main_Workshop_ML_ReinforcementLearning_Presentation.tex: Intro, Concepts, MDP, Q-Learning, Deep Q-Learning & Modern RL, Tools & Frameworks, Applications |
MDPs, Q-learning, deep Q-learning, RLlib, OpenAI Gym, tic-tac-toe implementation |
| Software Engineering | Main_Workshop_Tech_Software_Presentation.tex |
Complexity, data structures (arrays/queues/maps/trees/graphs), algorithms (recursion/search/sort/dynamic programming), system design, LeetCode practice |
| All-in-one ML bundle | Main_Workshop_MachineLearning_Presentation.tex |
All 5 ML-specific workshops chained together (no Python, no demos) |
Beyond the courses and workshops above, dozens of independent 1-hour seminars exist. A sample by theme:
- AI for different audiences (each now includes ChatGPT coverage folded in, at a depth matched to its audience): All Tech, All Non-Tech, Educators, Kids, Biz Leaders, Tech Leaders, Project Managers, With ML
- Deep dives / overviews: Data Concepts, DL Foundations, Deep NLP, Word Embeddings
- Deep Learning platforms: TensorFlow, PyTorch, Data + TensorFlow, Satellite Imagery
- Graph topics: Neo4j, Graph Data Science, Graph + NLP, Graph RAG (Knowledge Graphs: see the Knowledge Graphs workshop above)
- Applied ML: Explainable AI, Matrix Profile, SQL + RAG (Reinforcement Learning: see the Reinforcement Learning workshop above)
- Multi-agent frameworks: Multi-Agent Decision Systems (MADS): a configuration-driven multi-agent orchestration framework (Oracle/Specialist/Synthesizer architecture, Game Theory, Mental Models, TRIZ domains)
- Career & meta: Career in Data Science (Short version), Gartner Hype Cycles, LaTeX for Research
- Hands-on tool workshops: Claude Code, OpenCode
This list is a sample, not exhaustive: every Main_Seminar_*_Presentation.tex in LaTeX/ is an independent, compilable session; browsing that naming pattern directly is the fastest way to find something not listed here.