🌟 Deep Learning theory with Python, TensorFlow, and Keras

Welcome to the Deep Learning Project Repository – a comprehensive collection of practical deep learning examples, tutorials, and mini-projects built using Python, TensorFlow, and Keras. This repository is ideal for students, researchers, and AI enthusiasts who want to learn, implement, and master deep learning techniques through hands-on coding.

Welcome to the A-Z Guide to Deep Learning repository! This comprehensive supplement serves as your gateway to the expansive world of Deep Learning, offering in-depth coverage of algorithms, statistical methods, and techniques essential for mastering this cutting-edge field.

Overview👋🛒

The A-Z Guide to Deep Learning is designed to provide a comprehensive roadmap for both beginners and experienced practitioners seeking to delve into the realm of Deep Learning. Whether you're just starting your journey or looking to expand your expertise, this repository offers a wealth of resources to support your learning and exploration.

Features👋🛒

1- Extensive Coverage: Explore a wide range of topics, including fundamental concepts, advanced algorithms, statistical methods, and practical techniques crucial for understanding and implementing Deep Learning models.

2-Hands-On Implementations: Dive into practical implementations of Deep Learning algorithms and techniques using Python, alongside detailed explanations, code examples, and real-world applications.

3-Progressive Learning Path: Follow a structured learning path that progresses from foundational concepts to advanced topics, ensuring a gradual and comprehensive understanding of Deep Learning principles and methodologies.

4-Supplementary Resources: Access supplementary materials, such as articles, tutorials, research papers, and curated datasets, to enrich your learning experience and stay updated with the latest developments in Deep Learning.

Contents

Fundamental Concepts: Covering essential concepts such as neural networks, activation functions, optimization algorithms, loss functions, and regularization techniques.

Advanced Algorithms: Exploring advanced Deep Learning architectures and algorithms, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and reinforcement learning.

Statistical Methods and Techniques: Discussing statistical methods and techniques commonly used in Deep Learning, such as hypothesis testing, probability distributions, dimensionality reduction, and Bayesian inference.

Why Contribute?

1- Share Your Expertise: If you have knowledge or insights in Deep learning , your contributions can assist others in learning and applying these concepts.

2-Enhance Your Skills: Contributing to this project offers a great opportunity to deepen your understanding of Deep learning . Writing, coding, or reviewing content will reinforce your knowledge while uncovering new areas of the field.

3- Collaborate and Connect: Join a community of like-minded individuals committed to advancing AI education. Work with peers, receive feedback, and build connections that may open up new opportunities.

4- Make a Difference: Your contributions can shape how others learn and engage with machine learning. By refining and expanding content, you help shape the education of future engineers and AI experts.

💡 How to Participate?

🚀 Fork & Star this repository

👩‍💻 Explore and Learn from structured lessons

🔧 Enhance the current blog or code, or write a blog on a new topic

🔧 Implement & Experiment with provided code

🤝 Collaborate with fellow DL enthusiasts

📌 Contribute your own implementations & projects

📌 Share valuable blogs, videos, courses, GitHub repositories, and research websites

🎓 Enrolled Courses

Please enrolled in the following courses to strengthen knowledge and practical skills in Deep Learning. These courses are designed to provide both theoretical understanding and hands-on experience with real-world DL applications.

🔗 Improving Deep Neural Networks!

1- Covers foundational concepts such as Optimization Algorithms,Hyperparamter tunning etc.

🔗 Deep Learning- Neural Network

1- Focuses Funcation Concept of deep learning ,such as ,Deep learning, ANN etc

💡 These courses are part of a structured Deep Learningcurriculum offered by Coursera, designed by Coursera team, and emphasize practical implementation using Python and deep learning libraries.

Star this repo if you find it useful ⭐

🌍 Join Our Community

🔗 YouTube Channel

🔗 SubStack Blogs

🔗 Facebook

🔗 LinkedIn

📬 Need Help? Connect with us on WhatsApp

📬 Stay Updated with Weekly Deep Learning Lessons!

Never miss a tutorial! Get weekly insights, updates, and bonus content straight to your inbox.
Join hundreds of Deep Learning learners on Substack.

👉 Subscribe to Our Deep Learning Newsletter ✨

💡 Optional Badge (to make it pop)

---

Course 1 - 🧠Deep Learning-Neural Networks

Week 1-📚Chapter1: Introduction of Deep learning

Topic Name/Tutorial	Video	Code	Todo list
✅1-Understanding Basic Neural Networks g	1-2-3-4-5	Content 3
✅2-Supervised Learning with Neural Networks⭐	1	Content 6
✅3-Exploring the Different Types of Artificial Neural Networks⭐	-1	---
✅4- Why is Deep Learning taking off?⭐	1	---
✅5-Best Free Resources to Learn Deep learning (DL)⭐	---	---
✅6-GPU-CPU-TPU⭐	---	---	write blog

Week 2-📚Chapter1:2 Logistic Regression as a Neural Network

Topic Name/Tutorial	Video	Notebook
✅1- Binary Classification-s	1	Content 3
✅2- Logistic Regression-s	1-2	Content 6
✅3- Understanding the Logistic Regression Cost Function-S	1	---
✅4-Understanding the Logistic Regression Gradient Descent-s	1-2	---
✅5-Intuition about Derivatives	1
✅6-Computation Graph⭐	1-2	---
✅*7-Derivatives with a Computation Graph	1	---
✅8-Logistic Regression Gradient Descent⭐	1	---
✅9-Gradient Descent on m Examples⭐	1

Week 3-📚Chapter 3 Python and Vectorization

Topic Name/Tutorial	Video	Notebook
✅1-Vectorization⭐	1
✅2-More Vectorization Examples⭐	1
✅3-Vectorizing Logistic Regression⭐	1
✅4-Vectorizing Logistic Regression’s Gradient Output⭐	1

Week 4-📚Chapter4: Shallow Neural Network

Topic Name/Tutorial	Video	Notebook	Extra Reading
✅1-Neural Networks Overview⭐	1-2		Tiny Neural Networks-Paper
🌐2-Neural Network Representation⭐	1
🌐3-Computing a Neural Network's Output⭐	1-2
🌐4-Vectorizing Across Multiple Examples	1
🌐5-Explanation for Vectorized Implementation	1
🌐6-Activation functions-Copy fro courseteach	1
🌐7-Why do you need Non-Linear Activation Functions?	1
🌐8-Derivatives of Activation Functions?	1
🌐9-Gradient Descent for Neural Networks?	1
🌐10-Backpropagation Intuition?	1
🌐11-Random Initialization?	1
🌐12-NoProp, does not even require a Forward pass?🧠✨	1

Week 5-📚Chapter5:Deep Neural Network

Topic Name/Tutorial	Video	Notebook
🌐1-Deep L-layer Neural Network	1
🌐2-Forward Propagation in a Deep Network	1
🌐3-Getting your Matrix Dimensions Right	1
🌐4-Why Deep Representations?	1
🌐5-Building Blocks of Deep Neural Networks?	1
🌐6-Forward and Backward Propagation?	1
🌐7-Parameters vs Hyperparameters	1

Course 2 - 🧠Improving Deep Neural Network

Week 1-📚Chapter1:Practical Aspects of Deep Learning

Topic Name/Tutorial	Video	Code
🌐1-Train / Dev / Test sets	1
🌐2-Bias Variance	1
🌐3-Basic Recipe for Machine Learning	-1
🌐4- Regularization⭐	1-2
🌐5-Why Regularization Reduces Overfitting	1-2	---
🌐6- Dropout Regularization	1-2-3
🌐7- Other Regularization Methods	1-2
🌐8- Normalizing Inputs	1
🌐9- Vanishing-Exploding Gradients	1
🌐10- Weight Initialization for Deep Networks	1
🌐11- Numerical Approximation of Gradients	1
🌐12- How Gradient Checking Can Save You Time and Help Debug Neural Networks	1-2

Week 2-📚Chapter2:Optimization Algorithms

Dive deeper into neural network optimization techniques in Week 2 of our Deep Learning series. This chapter covers key optimization algorithms that help accelerate and stabilize training, with hands-on videos, Medium tutorials, and Colab notebooks for each concept.

Topic Name/Tutorial	Video	Code	Extra Reading
1-Mini-batch Gradient Descent⭐	1
🌐2-Understanding Mini-batch Gradient Descent⭐	1
🌐3-Exponentially Weighted Averages⭐	1-2
🌐4-Understanding Exponentially Weighted Averages⭐	1
🌐5-Bias Correction in Exponentially Weighted Averages⭐	1
🌐6-Gradient Descent with Momentum⭐	1
🌐7-RMSprop⭐	1-2
🌐8-Adam Optimization Algorithm	1		1
🌐9-Learning Rate Decay	1
🌐10-The Problem of Local Optima	1

Week 3-📚Chapter3:Hyperparameter tunning , Batch Normalization and Programming Frameworks

Topic Name/Tutorial	Video	Code	Note	Difficulty level
1-Tuning Process	1		---	Intrmediate
2-Using an Appropriate Scale to pick Hyperparameters	1		---	Intrmediate
3-Hyperparameters Tuning in Practice Pandas vs Caviar	1		LINK	Intrmediate
4-Normalizing Activations in a Network	1		LINK	Intrmediate
5-Fitting Batch Norm into a Neural Network	1		LINK	Intrmediate

Course 3 - 🧠Structuring Machine Learning Projects

Week 1-📚Chapter1:Practical Aspects of Deep Learning

Topic Name/Tutorial	Video	Code
🌐1-Train / Dev / Test sets	1

Course 4 - 🧠Convolutional Neural Networks

Week 1-📚Chapter1:Practical Aspects of Deep Learning

Topic Name/Tutorial	Video	Code
🌐1-Train / Dev / Test sets	1

Course 5 - 🧠Sequence Models

Week 1-📚Chapter1:Practical Aspects of Deep Learning

Topic Name/Tutorial	Video	Code
🌐1-Train / Dev / Test sets	1

Course 5 - 🧠Graph Neural Networks

Week 1-📚Chapter1:Practical Aspects of Deep Learning

Topic Name/Tutorial	Video	Code
🌐1-Train / Dev / Test sets	1

Course 6 - 🧠Autoencoders

Week 1-📚Chapter1:Practical Aspects of Deep Learning

Topic Name/Tutorial	Video	Code	Extra Resources
🌐1-Introduction to Autoencoders	1		1

Course 7 -⚡ Transformers

Week 1-📚Chapter1:Practical Aspects of Deep Learning

Topic Name/Tutorial	Video	Code	Extra Resources
🌐1-Introduction to Transformers	1		1

Course 7 -Transfer Learning and Distillation

Week 1-📚Chapter1:Practical Aspects of Deep Learning

Topic Name/Tutorial	Video	Code	Extra Resources
🌐1-Transfer Learning	1		1

🗞️📚Other Best Free Resources to Learn Deep Learning

• Assignment 1: Python Basics with Numpy

##Alogrithems - DL0101EN-3-1-Regression-with-Keras-py-v1.0.ipynb - DL0101EN-3-2-Classification-with-Keras-py-v1.0.ipynb - Keras - Tutorial - Happy House v1.ipynb - Keras_for_Beginners_Implementing_a_Convolutional_Neural_Network - Keras_for_Beginners_Building_Your_First_Neural_Network.ipynb

• Need to Implement
  • Text Classification — CNN with LSTM
  • Step-by-Step Guide — Building a Prediction Model in Python
• Important Website
  • victorzhou

📕 Deep Learning Resources

👁️ Chapter1: - Free Courses

Title/link	Description	Reading Status
✅1-Deep Learning Specialization by Andrew	by andrew,Cousera,Good	InProgress
✅2-Deep Learning(Yann LeCun & Alfredo Canziani)	It is free course and it contain notes and video	Pending
✅2-eural Networks: Zero to Hero	It is free course and it contain notes and video,Andrej Karpathy	Pending
✅3-Practical Deep Learning	It is free course and it contain notes and video,Andrej Karpathy	Pending
✅4-Deep Learning- Texas Austin	It is free course and it contain notes and video,Andrej Karpathy	Pending
✅5-Neural Networks / Deep Learning	StatQuest with Josh Starmer	Pending
✅6-Zero to Mastery Learn PyTorch for Deep Learning	Learn PyTorch for Deep Learning: Zero to Mastery book	Pending
✅7-Generative AI for Everyone by andrew	Learn PyTorch for Deep Learning: Zero to Mastery book	Pending

🔹 Chapter 4: - List of Deep Learning Models

Deep Learning models come in different families, designed for specific tasks such as vision, language, speech, and generative AI. Below is a categorized list of important models.

Category	Models	Notes
Computer Vision (Classification)	AlexNet, VGG, ResNet, DenseNet, EfficientNet, ViT 🔴🔵, Swin Transformer 🔴🔵, ConvNeXt 🔵	Image classification (CNNs & Vision Transformers)
Computer Vision (Detection & Segmentation)	R-CNN, Fast R-CNN, Faster R-CNN, YOLO, SSD, RetinaNet, DETR 🔴🔵, Mask R-CNN, FCN, U-Net, DeepLab, PSPNet, SegFormer 🔴🔵, SAM 🔴🔵	Object detection & pixel-level segmentation
Generative Models	Autoencoders, VAE, GAN, DCGAN, CycleGAN, StyleGAN, BigGAN, Diffusion Models (DDPM 🔵), DALL·E 🔴🔵, Stable Diffusion 🔵	Image, video & art synthesis
NLP (Language Models)	Word2Vec, GloVe, ELMo, BERT 🔴, RoBERTa 🔴, XLNet 🔴, ALBERT 🔴, GPT family 🔴, T5 🔴, BART 🔴, DistilBERT 🔴, LLaMA 🔴🔵, Falcon 🔴🔵, Mistral 🔴🔵	Text representation, transformers & LLMs
Speech & Audio	DeepSpeech, Wav2Vec 🔴, HuBERT 🔴, Whisper 🔴🔵, Conformer 🔴🔵	Speech recognition & audio understanding
Multimodal Models	CLIP 🔴🔵, Flamingo 🔴🔵, Kosmos-1 🔴🔵, GPT-4 🔴🔵, Gemini 🔴🔵	Models combining vision, text, and sometimes audio
3D & Video Models	3D CNNs, C3D, I3D, PointNet, NeRF 🔵, Video Swin Transformer 🔴🔵	3D recognition & video understanding

---

Legend:

• 🔴 Transformer-based
• 🔵 Introduced after 2020

---

👁️ Chapter2: - Important Website

Title	Description	Status
🌐1-Roadmap.sh	Provide complet Roadmap about AI Courses	---
🌐2-Bolt	write softare code and deployed	---
✅3-Kaggle Notebooks	offers up to 30 hours of free GPU time per week	---
✅4-Google Colab	Google Colab offers free GPU and TPU resources.	---
✅5-Amazon SageMaker	Amazon SageMaker Studio Lab offers free CPU and GPU. No credit card or AWS account required	---
✅6-Gradient/Paperspace	offers GPU and IPU instances with a free tier to get started	---
✅7-Microsoft Azure for Student Account	offers GPU and IPU instances with a free tier to get started	---
✅8-deeplearning.neuromatch.io	offers GPU and IPU instances with a free tier to get started	---
✅9-Deep Learning Institute-nvidia	Free Course nvidia	---
✅10-Building a GPT from Scratch	This page (from the "Building a GPT from Scratch" section of Simon Thomine’s Deep Learning course) walks you through implementing a character-level transformer-based language model in PyTorch—from dataset preprocessing to self-attention, multi-head attention, and full transformer blocks—using Molière’s plays as training data	---
✅11-DEEP LEARNING	DS-GA 1008 · SPRING 2021 · NYU CENTER FOR DATA SCIENCE	---

👁️ Chapter2: - Important Notbook

Title	Description	Status
✅1-Understanding Deep Learning	Python notebooks covering the whole text	---

👁️ Chapter3: - Important Social medica Groups

Title/link	Description	Code
🌐1- Computer Science courses with video lectures	It is Videos and github	---

👁️ Chapter4: - Free Books

Title/link	Description	Code
✅1- Linear Algebra and Optimization for Machine Learning	It is Videos and github	---
✅1- Dive into Deep Learning	Interactive deep learning book with code, math, and discussions	---

👁️ Chapter5: - Github Repository

Title/link	Description	Status
✅1- Computer Science courses with video lectures	It is Videos and github	Pending
✅2- ML YouTube Courses	Github repisotry contain couress	Pending
✅3- ml-roadmap	Github repisotry contain couress	Pending
✅4-courses & resources	Github repisotry contain couress	Pending
✅5-PyTorch Fundamentals	Github repisotry contain couress	Pending
✅6-Advanced RAG Techniques: Elevating Your Retrieval-Augmented Generation Systems	Github repisotry contain couress	Pending
✅7-Awesome LLM Apps	Github repisotry contain couress	Pending

👁️ Chapter1: - Tools, Frameworks & Platforms

Deep Learning has grown into a vast ecosystem of tools, libraries, and platforms. Each serves a different purpose—from building models to deploying them, managing experiments, and scaling in production. Below is a categorized overview of the most widely used ones.

🔧 Core Frameworks

Title	Description	Tag
✅ TensorFlow	Google’s end-to-end open-source library for ML/DL, widely used for research and production.	Framework
✅ PyTorch	Facebook’s deep learning framework, popular for flexibility and research.	Framework
✅ Keras	High-level neural network API running on top of TensorFlow, user-friendly for rapid prototyping.	Framework
✅ JAX	High-performance ML research library by Google with auto-differentiation & GPU/TPU support.	Framework
✅ MXNet	Apache’s deep learning framework, once widely used by AWS for large-scale DL.	Framework
✅ Theano (legacy)	Pioneering DL library, now discontinued but historically important.	Legacy

---

🧰 Developer & Experimentation Tools

Title	Description	Tag
✅ Jupyter Notebook	Interactive coding environment for ML/DL experiments.	Developer Tools
✅ Google Colab	Free cloud-based Jupyter notebooks with GPU/TPU access.	Developer Tools
✅ Kaggle Kernels	Cloud notebooks with datasets, GPUs, and competitions.	Developer Tools
✅ Gradio	Build and share ML-powered apps easily with a web UI.	Developer Tools
✅ Streamlit	Create interactive dashboards and ML applications quickly.	Developer Tools

---

📊 Experiment Tracking & MLOps

Title	Description	Tag
✅ Weights & Biases (W&B)	Track experiments, visualize results, and manage ML projects.	MLOps
✅ MLflow	Open-source platform for managing ML lifecycles.	MLOps
✅ Neptune.ai	Metadata store for ML model tracking and collaboration.	MLOps
✅ DVC	Version control system for ML datasets and models.	MLOps
✅ Comet ML	Experiment tracking and visualization for ML/DL.	MLOps

---

🧠 Pre-trained Models & Model Hubs

Title	Description	Tag
✅ Hugging Face	Central hub for transformers, models, datasets, and communities.	Model Hub
✅ TensorFlow Hub	Repository of pre-trained TensorFlow models.	Model Hub
✅ PyTorch Hub	Pre-trained models ready to use with PyTorch.	Model Hub
✅ ONNX Model Zoo	Open Neural Network Exchange pre-trained models.	Model Hub

---

🖥️ Deployment & Serving

Title	Description	Tag
✅ TensorFlow Serving	Production-grade system for serving TF models.	Deployment
✅ TorchServe	Model serving library for PyTorch.	Deployment
✅ ONNX Runtime	Run ML models across frameworks and hardware.	Deployment
✅ NVIDIA Triton Inference Server	Scalable deployment for GPU-accelerated inference.	Deployment

---

☁️ Cloud Platforms for DL

Title	Description	Tag
✅ Google Vertex AI	End-to-end ML/DL platform on Google Cloud.	Cloud
✅ AWS SageMaker	Amazon’s ML/DL service for building and deploying models.	Cloud
✅ Azure ML Studio	Microsoft’s ML/DL cloud environment.	Cloud
✅ Paperspace Gradient	Cloud GPUs for training and deployment.	Cloud
✅ Lambda Labs	GPU cloud and DL workstations.	Cloud

---

👁️ Chapter1: - Important Research Papers

Title	Description	Status
✅1- Learning to learn by gradient descent by gradient descent	---	Pending
✅2- Computer Science courses w	It is Videos and github	---

💻 Workflow:

• Fork the repository

• Clone your forked repository using terminal or gitbash.

• Make changes to the cloned repository

• Add, Commit and Push

• Then in Github, in your cloned repository find the option to make a pull request

print("Start contributing for Deep Learning")

⚙️ Things to Note

• Make sure you do not copy codes from external sources because that work will not be considered. Plagiarism is strictly not allowed.
• You can only work on issues that have been assigned to you.
• If you want to contribute the algorithm, it's preferrable that you create a new issue before making a PR and link your PR to that issue.
• If you have modified/added code work, make sure the code compiles before submitting.
• Strictly use snake_case (underscore_separated) in your file_name and push it in correct folder.
• Do not update the README.md.

✨Top Contributors

We would love your help in making this repository even better! If you know of an amazing AI course that isn't listed here, or if you have any suggestions for improvement in any course content, feel free to open an issue or submit a course contribution request.

                   Together, let's make this the best AI learning hub website! 🚀

Thanks goes to these Wonderful People. Contributions of any kind are welcome!🚀