Deep Learning A-Z

Welcome to the Deep Learning A-Z repository! This collection is designed to guide you through the foundational concepts and implementations of various deep learning architectures, providing hands-on experience with each model type.

📚 Repository Overview

This repository is structured into six main sections, each focusing on a different deep learning architecture:

1. Artificial Neural Networks (ANN) : Explore the basics of neural networks, including forward and backward propagation, activation functions, and training processes.
2. Convolutional Neural Networks (CNN) : Delve into models primarily used for image recognition and processing, understanding convolutional layers, pooling, and feature extraction.
3. Recurrent Neural Networks (RNN) : Learn about networks designed for sequential data, such as time series or natural language, and grasp concepts like looping mechanisms and memory retention.
4. Self-Organizing Maps (SOMs) : Study unsupervised learning techniques that visualize and interpret complex data patterns through dimensionality reduction.
5. Boltzmann Machines (BM) : Investigate stochastic recurrent neural networks capable of learning complex probability distributions over datasets.
6. AutoEncoders (AE) : Understand models used for data compression and noise reduction by learning efficient codings of input data.

🛠️ Getting Started

To effectively utilize this repository, follow these steps:

1. Clone the Repository :

   git clone https://github.com/dash7ou/deep-learning.git
   cd deep-learning
   ```

1. Set Up the Environment :

• It's recommended to use a virtual environment to manage dependencies.
• Install the required packages using the provided requirements.txt file:

  pip install -r requirements.txt
  ```

• Alternatively, if you use conda, create an environment using the environment.yml file:

  conda env create -f environment.yml
  conda activate deep-learning
  ```
  

1. Explore the Notebooks :

• Each section contains Jupyter Notebooks with detailed explanations and code implementations.
• Launch Jupyter Notebook:

  jupyter notebook
  ```

• Navigate to the desired section and open the notebook to begin your learning journey.

📂 Repository Structure

deep-learning/
├── 01- Artificial Neural Networks (ANN)/
│   ├── ann_introduction.ipynb
│   ├── ann_training.ipynb
│   └── ...
├── 02- Convolutional Neural Networks (CNN)/
│   ├── cnn_introduction.ipynb
│   ├── cnn_image_classification.ipynb
│   └── ...
├── 03- Recurrent Neural Networks (RNN)/
│   ├── rnn_introduction.ipynb
│   ├── rnn_time_series.ipynb
│   └── ...
├── 04- Self Organizing Maps (SOMs)/
│   ├── som_introduction.ipynb
│   └── ...
├── 05- Boltzmann Machines (BM)/
│   ├── bm_introduction.ipynb
│   └── ...
├── 06- AutoEncoders (AE)/
│   ├── ae_introduction.ipynb
│   └── ...
├── environment.yml
├── requirements.txt
└── README.md
```

🤝 Contributing

Contributions are welcome! If you have suggestions or improvements, please open an issue or submit a pull request.

📧 Contact

For any questions or inquiries, feel free to reach out:

• GitHub: dash7ou
• LinkedIn: Mohammed M R Zourob

Happy Learning!