Machine and Deep Learning Study Roadmap

Overview

This repo includes roadmaps, resources, courses and their projects, and notes that I am following to build a strong foundation in machine and deep learning.

---

Contents

• Prerequisites: Quick revision on NumPy, Pandas, and Matplotlib.
• MIT 6.S191: Introduction to Deep Learning.
• PyTorch Course: Zero to Mastery Learn PyTorch for Deep Learning.
• Projects: Contains most course projects; larger projects have their own repos linked below.
• LLM from Scratch Course
• ITI Summer Training: Machine Learning (supervised and unsupervised).
• Graduation Project Notes: Research notes from my Bachelor’s degree project on Parkinson’s disease (not the actual project, but concepts explored and ML-related notes for future reference).
• Individual Searches: Contains study notes on individual topics studied/revised.
• Reinforcement Learning: Contains all the reinforcement learning courses, resources, and notes.
• AI-Agents: Contains courses on LangChain, LangGraph, and other ai-agents related courses.
• Interview-prep: Contains important interview questions for variuos topics about ML.

---

Resources & Links

Roadmaps:

• How to Learn Machine Learning in 2024 (7-step roadmap)
• Machine-Learning-Roadmap
• advanced-machine-learning-engineer-roadmap-2024
• AI-ML-Roadmap-from-scratch

Courses:

• MIT 6.S191: Introduction to Deep Learning (highly recommended)
• PyTorch for Deep Learning & Machine Learning – Full Course
  • GitHub Repo
  • Book Page
• Dive into Deep Learning: Interactive deep learning book with code, math, and discussions
• LLMs from Scratch
• Stanford Courses:
  • Stanford CS229: Machine Learning
  • Stanford CS230: Deep Learning
  • Stanford CS336: Language Modeling from Scratch
  • Stanford CS236: Deep Generative Models
  • Stanford CS234: Reinforcement Learning
  • Stanford CS224R Deep Reinforcement Learning
  • Statistical Learning with Python

Online Tutorials & Blogs:

Quick revision:

• All Machine Learning Algorithms Explained in 17 Min
• 15 Machine Learning Lessons I Wish I Knew Earlier
• Great ML/DL YT channel (StatQuest with Josh Starmer)

Interview questions:

• Cracking Machine Learning Interview: A repository to prepare you for your machine learning interview, involving most of the questions asked by all the tech giants and local companies. Do this to Ace your Machine Learning Engineer Interviews.
• Data Science Interview Resources: A repository listing out the potential sources which will help you in preparing for a Data Science/Machine Learning interview. New resources added frequently.
• machine learning interview questions: This repository is to prepare for Machine Learning interviews.

Useful Websites:

• Browse State-of-the-Art
• Hugging Face Models
• timm (PyTorch Image Models) Library
• Google dataset search

---

Projects & Practice

• Older projects in this repo are mostly drafts and unpolished experiments.
• More recent projects were developed in their own dedicated repositories (including experiments and failed attempts), and are no longer included in this repo.
• For complete projects, please check the linked repositories.

Main Projects

• Project Mozart: Custom Transformer-based music generation.
• Brain Tumor Segmentation: Deep learning model for semantic segmentation of brain tumors from MRI scans.
• German Tutor: AI-powered German language learning assistant.
• CelluScan: Automated blood cell classification with Vision Transformer.
• Real-Time Number Detector Web App: Trained on MNIST + custom data.

PyTorch Course Tasks

• Fashion MNIST Model (with confusion matrix, Chapter 3)
• Multi-class Evaluation Model (Non-linear, Chapter 2)
• Linear Regression Model (Chapter 1)
• Final Project:
  • Food MINI Model: Experiment tracking and model deployment.

---

Machine Learning & Deep Learning Mastery Checklist

This is a personal checklist of the most important topics I want to learn in Machine Learning and Deep Learning. I use it to keep track of what I’ve already studied, what I’m currently working on, and what I still need to learn.

The list is always growing as I go deeper into the field and discover new concepts, tools, and techniques. It helps me stay organized and maintain a clear learning path instead of studying topics randomly.

1. Mathematical Foundations (from college)

• Linear Algebra (vectors, matrices, eigenvalues, SVD)
• Calculus (gradients, Jacobians, chain rule)
• Probability & Statistics (distributions, expectation, Bayes)
• Optimization

---

2. Classical Machine Learning

• Linear Regression
• Logistic Regression
• Decision Trees / Random Forests
• Boosting and Bagging
• Support Vector Machines (SVM)
• K-Nearest Neighbors (KNN)
• Naive Bayes (Multinomial, Gaussian)
• Gradient Boosting / XGBoost
• K-Means & other clustering methods (Hierarchical clustering, DBSCAN)
• Gaussian Mixture Models (GMM)
• Dimensionality Reduction (PCA)
• Bias–Variance Tradeoff
• Cross-validation
• Regularization (Ridge (L2) and Lasso (L1))
• Evaluation Metrics (Accuracy, Precision, Recall, F1, ROC, AUC)
• Feature Engineering / Normalization

---

3. Core Deep Learning

• Perceptron, Feedforward Networks
• Activation Functions (ReLU, Sigmoid, Tanh, GELU, etc.)
• Backpropagation
• Weight Initialization (Xavier, Kaiming)
• Dropout / BatchNorm / LayerNorm
• Loss Functions (MSE, Cross-Entropy, BCE, etc.)
• Learning Rate Schedules
• Early Stopping
• Gradient Clipping
• Data Augmentation
• Mixed Precision Training

---

4. Convolutional Neural Networks (CNNs)

• Convolution / Pooling / Padding
• LeNet
• AlexNet
• VGG
• ResNet
• EfficientNet
• Transfer Learning
• Object Detection (YOLO)
• Segmentation (U-Net, Mask R-CNN)

---

5. Recurrent and Sequential Models

• RNNs
• LSTMs
• GRUs
• Sequence-to-Sequence Models
• Attention Mechanisms
• Encoder–Decoder Architectures

---

6. Transformers and Attention Models

• Self-Attention & Multi-Head Attention
• Transformer Architecture (Encoder, Decoder)
• Vision Transformer (ViT)
• BERT & GPT-style models (encoder vs decoder-only)
• Positional Encoding
• Fine-tuning large models
• Top-k, Top-p (nucleus) sampling

---

7. Generative Models

• Autoencoders (AE)
• Variational Autoencoders (VAE)
• Generative Adversarial Networks (GANs)
• Diffusion Models
  • DDPM
  • Stable Diffusion
  • ControlNet
• Transformers
• Flow-based Models (RealNVP, Glow)

---

8. Self-Supervised / Representation Learning

• Contrastive Learning (SimCLR, MoCo)
• Masked Autoencoders (MAE, BEiT)
• DINO / CLIP (cross-modal self-supervision)

---

9. Reinforcement Learning (RL)

Foundations

• Markov Decision Processes (MDPs)
• Bellman Equations (Value / Q-function / Advantage function)
• Exploration vs. Exploitation (ε-greedy, softmax policies)
• Policy Evaluation & Policy Improvement
• Value Iteration / Policy Iteration

Core RL Algorithms

• Monte Carlo Methods (First-visit / Every-visit)
• Temporal Difference Learning (TD(0), TD(λ))
• SARSA / Q-Learning
• Deep Q-Network (DQN)
• Improvements: Double DQN, Dueling DQN, Prioritized Replay

Policy Gradient & Actor–Critic Methods

• Policy Gradient (REINFORCE)
• Actor–Critic (A2C, A3C)
• PPO (Proximal Policy Optimization)
• TRPO (Trust Region Policy Optimization)

Continuous Control Algorithms

• DDPG (Deep Deterministic Policy Gradient)
• TD3 (Twin-Delayed DDPG)
• SAC (Soft Actor–Critic)

Model-Based & Advanced RL

• Planning (Dyna-Q)
• Model-Based RL (Dreamer, MuZero-style)
• Hierarchical RL (Options Framework)
• Meta-RL (MAML, RL²)
• Multi-Agent RL (MADDPG, QMIX)
• Offline RL (CQL, Conservative Q-Learning)
• Imitation Learning (BC, GAIL)
• RLHF (Reinforcement Learning from Human Feedback)

Practical Skills

• Learn OpenAI Gym / Gymnasium environments (spaces, wrappers, vector envs)
• Implement RL algorithms from scratch in PyTorch:
  • Q-learning (tabular)
  • DQN (with Q + target network)
  • REINFORCE
  • Actor–Critic (A2C)
  • PPO & GRPO (only implemented PPO but studied GRPO)
  • DDPG / TD3 / SAC (SAC only)
• Learn stable-baselines3 usage and comparison
• Logging RL experiments (TensorBoard, Weights & Biases)

---

10. AI Agents & Autonomous Systems

Agent Architectures

• ReAct (Reason + Act)
• AutoGPT / BabyAGI-style loop
• Planning + Reflection loops
• Tool-using agent frameworks (LangChain / LlamaIndex)

Memory & Retrieval

• Retrieval-Augmented Generation (RAG)
• Vector Databases (FAISS, Chroma, Milvus)
• Long-term memory strategies (episodic, semantic)

Integrating RL with Agents

• RL-driven tool selection
• Feedback loops for improving agent behavior
• Multi-agent coordination & communication

---

11. Deployment & MLOps

• Hugging Face deployment
• TorchScript / ONNX model export
• FastAPI or Flask inference servers
• Dockerization for reproducible deployment
• GPU inference optimization (mixed precision, batching)
• Model quantization / pruning
• Distributed training (PyTorch DDP / DeepSpeed)
• CI/CD for models (GitHub Actions + versioning)
• Monitoring / logging in production (W&B, Mlflow, TensorBoard)

---

12. Practical / Projects

• Build and train models from scratch
• Reproduce architectures (ViT, Transformer, etc.)
• Train a symbolic music generation Transformer
• Generate synthetic dataset using generative models.
• Visualize training metrics (TensorBoard, W&B)
• Use pretrained models (Hugging Face)
• Handle datasets and dataloaders efficiently
• Implement an RL environment and agent
• Build a tool-using AI agent with memory