Deep Learning

This repository contains a collection of Jupyter Notebooks exploring Deep Learning techniques with modern neural network architectures and workflows.

Topics Covered

• Convolutional Neural Networks (CNNs)
• Transfer Learning and Fine-Tuning with pretrained models
• Recurrent Neural Networks (RNNs, LSTMs, GRUs)
• Custom and pretrained Embeddings
• Input preprocessing layers (Keras)
• Natural Language Processing (NLP)
• Introductory Generative AI techniques for images

Repository Structure

deep_learning/
│
├── src/                  # Source code for the projects
│   ├── data/             # Data-related files
│   ├── img/              # Images related to the projects
│   ├── models/           # Trained models saved in .pkl or .joblib
│   ├── notebooks/        # Main Jupyter Notebooks, organized by topic
│   └── utils/            # Utility functions (data processing, model setup, etc.)
│
├── .gitignore            # Specifies files and directories ignored by Git
├── LICENSE               # Main License information
├── README.md             # Main documentation for the project
└── requirements.txt      # Python dependencies

Running on Google Colab or Similar Cloud Platforms

All Notebooks are ideal for running on cloud-based platforms like Google Colab or Kaggle Kernels due to their ease of use and availability of powerful GPU/TPU resources. You can easily upload your dataset to Google Colab and run the notebooks with minimal setup.

Requirements

Make sure to install the dependencies listed in requirements.txt:

pip install -r requirements.txt

Coming Soon

• Transformers
• Generative models using diffusion techniques
• Interactive error analysis and model visualization tools
• Cross-validation strategies and advanced regularization techniques

Contributing

If you have any suggestions or improvements, feel free to open an issue or submit a pull request. Your contributions are always welcome!

Contact

If you have any questions or want to get in touch, please feel free to reach out to me at LinkedIn.