Advanced Deep Learning

This repository contains implementations of various advanced deep learning concepts and architectures. Each implementation serves as both a learning resource and a practical reference for understanding complex deep learning models and techniques.

Implemented Topics

1. Autoregressive Generative Models

   • PixelCNN
   • PixelRNN

2. Contrastive Representation Learning

   • Contrastive Predictive Coding
   • SimCLR

3. Unsupervised Representation Learning

   • CutMix
   • Image Rotation Prediction

4. Text (Language) Modelling

   • Neural Variational Document Model
   • Multi-Level Latent Variable
   • Timestep-Wise Regularization

5. Generative Adversarial Networks

   • BiGAN
   • BigBiGAN
   • InfoGAN-BigBiGAN

6. Image Classification

   • EfficientNet-B0
   • VGGNet
   • ResNet
   • Inception
   • Xception

7. Text Classification

   • BERT
   • Fasttext
   • Word2vec
   • Glove

8. Visual Question Answering

   • ResNet+Glove

Implementation Details

Each implementation includes:

• Model architecture and implementation
• Training and evaluation code
• Example usage
• Key concepts and techniques used
• Performance metrics and results

Getting Started

1. Clone the repository:

git clone https://github.com/yourusername/Advanced-Deep-Learning.git
cd Advanced-Deep-Learning

2. Set up the environment:

# Create a virtual environment (recommended)
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

3. Navigate to the specific implementation you're interested in and follow its README for detailed instructions.

Requirements

• Python 3.7+
• PyTorch >= 1.7.0
• Additional dependencies are specified in each implementation's requirements.txt

Contributing

Contributions are welcome! Feel free to:

• Add new implementations
• Improve existing implementations
• Fix bugs
• Add documentation
• Share your results and findings

License

This project is licensed under the MIT License - see the LICENSE file for details.