DeepLearning 📘

A comprehensive repository for my Deep Learning study, implementation, and practice projects.
This includes lecture materials, theoretical notes, resources, self-implemented models, and hands-on notebooks to build strong fundamentals and practical skills in Deep Learning.

---

📍 Overview

This repository contains:

🔹 LectureMaterial

Notes, slides, and code from theory sessions. Includes key concepts of neural networks, learning algorithms, activation functions, loss functions, optimization techniques, etc.

🔹 andrew-ng-CS299(Thoritical)-Notes-material

Theoretical notes based on CS299 or related foundational Deep Learning courses.

🔹 Resource

General resources, articles, external links, and cheatsheets that helped during study.

🔹 asg_sols

Assignment solutions for practice problems and coursework.

🔹 numpy-advance

Advanced exercises and implementations using NumPy to build deep understanding of vectorization and manual tensor operations.

🔹 self_implementation

My own implementations of core deep learning models from scratch (e.g., Perceptron, MLP, Backpropagation, etc.).

---

📂 Repo Structure

DeepLearning/

│

├── LectureMaterial/

├── andrew-ng-CS299(Thoritical)-Notes-material/

├── Resource/

├── asg_sols/

├── numpy-advance/

├── self_implementation/

├── .gitignore

├── README.md

---

🚀 Highlights & Implementations

Here are some of the key implementations (expand later with links & descriptions):

🧠 Basic Models Implemented

✔ Perceptron
✔ Multi-Layer Perceptron (MLP)
✔ Activation functions (ReLU, Sigmoid, Tanh)
✔ Forward & Backward propagation manually
✔ Loss functions (MSE, Cross-entropy)

🤖 Advanced Concepts (to be added)

✔ Training loops & weight optimization
✔ Batch normalization
✔ Dropout
✔ Regularization techniques

---

🛠 Tools & Libraries Used

The following tools and libraries are used across projects and notebooks:

Library	Usage
Python	Core language
NumPy	Core mathematical operations
Matplotlib / Seaborn	Visualization
Jupyter Notebook	Interactive experiments
Scikit-Learn	Data preprocessing & metrics
TensorFlow / PyTorch	Deep learning frameworks (future projects)

---

📖 References

This study is primarily based on:

🎓 Online NPTEL Deep Learning course – IIT Ropar concepts, models, and assignments 📚 Other online resources & research articles (to be added by you)

📌 How to Use This Repo

1. Explore folders based on topics.
2. Open relevant Jupyter Notebooks to understand implementations.
3. Use the code as templates for further experimentation.
4. Try to re-implement models from scratch to improve fundamentals.

---

🧩 Future Work (To Be Added)

✔ Sequential models (RNNs, LSTMs, GRUs)
✔ Attention Mechanisms & Transformers
✔ Practical applications (Vision, NLP)
✔ PyTorch end-to-end projects