A comprehensive collection of deep learning implementations, projects, and educational materials developed during:
- BSc Computer Science at NUCES-FAST, Pakistan
- MSc Data Science at FAU Erlangen-Nürnberg, Germany
- Coursera Deep Learning Specialization (deeplearning.ai)
- Various online learning platforms
This repository serves as a knowledge base showcasing fundamental to advanced deep learning concepts through practical implementations. Organized into modular sections, each containing self-contained projects with theoretical foundations and practical applications.
- Explainable AI (XAI): LIME, SHAP
- Sequence Modeling: Transformers, Attention Mechanisms
- Generative Models: GANs, VAEs
/Coursera_Deep_learning_specialization
- Complete implementations from Andrew Ng's Deep Learning Specialization
- Topics range from NumPy-based NN foundations to advanced CNNs
- Includes neural style transfer implementation
- Core architectures: FFNN, CNNs, RNNs
- Advanced implementations: ResNet in PyTorch
- Optimization techniques and best practices
- Text classification models
- Sequence-to-sequence implementations
- Transformer-based applications
/Standalone_Jupyter_Notebook_Projects
- Self-contained Jupyter notebooks with complete analysis
- Topic classification using Keras
- Model interpretation and visualization
- Comprehensive reports explaining concepts
- Frameworks: TensorFlow, Keras, PyTorch
- Languages: Python, NumPy
- Tools: Jupyter Notebook, Google Colab
- Concepts: From basic neural networks to cutting-edge architectures
This repository is actively maintained with new projects and improvements. Contributions and suggestions are welcome!
- T1: Task 1
- T2: Task 2