Introduction to Deep Learning 🧑‍💻

Welcome to the Introduction to Deep Learning repository! This repository provides a series of interactive Jupyter Notebook exercises designed to teach fundamental deep learning concepts through hands-on implementation and experimentation.

🗂️ Contents

📘 Notebooks

1. Single Neuron Model

   • Learn the basic building blocks of deep learning by implementing a single neuron.

2. Binary Classification

   • Explore binary classification problems and understand how to train a model for classification tasks.

3. Deep Neural Networks

   • Dive into deep learning by building and training multi-layered neural networks.

4. Dropout and Batch Normalization

   • Discover techniques to improve model performance and generalization using dropout and batch normalization.

5. Overfitting and Underfitting

   • Understand the challenges of overfitting and underfitting and learn how to mitigate them.

6. Stochastic Gradient Descent

   • Master the fundamentals of optimization with stochastic gradient descent

🌟 Version Control

This repository uses Git for version control. Clone the repository and track changes to improve collaboration and manage project versions.

🔧 Requirements

This tutorial requires the following packages:

• 🐍 Python version 3.5 or later (Python 3.4 should work fine; Python 2.7 might also work, but it’s not guaranteed! 😅)
• 📊 numpy version 1.10 or later: numpy.org
• 🧪 scipy version 0.16 or later: scipy.org
• 📈 matplotlib version 1.4 or later: matplotlib.org
• 📋 pandas version 0.16 or later: pandas.pydata.org
• 🛠️ scikit-learn version 0.15 or later: scikit-learn.org
• 🤖 keras version 2.0 or later: keras.io
• 🧠 tensorflow version 1.0 or later: tensorflow.org
• 📓 ipython/jupyter version 4.0 or later, with notebook support: jupyter.org

🚀 Getting Started

Prerequisites

• Python 3.7 or higher
• Jupyter Notebook or JupyterLab
• Recommended libraries:
  • numpy
  • matplotlib
  • tensorflow or pytorch

Installation

1. Clone the repository:

   git clone https://github.com/rusiru-erandaka/Introduction_to_Deep_learning.git

2. Navigate to the project directory:

   cd Introduction_to_Deep_learning

3. Install the required libraries:

   pip install -r requirements.txt

Running the Notebooks

1. Start Jupyter Notebook:

   jupyter notebook

2. Open any of the provided .ipynb files to begin exploring deep learning concepts interactively.

🎯 Learning Objectives

By completing these exercises, you will:

• Gain a strong foundational understanding of deep learning.
• Learn to implement and experiment with neural networks.
• Understand key concepts like overfitting, underfitting, and optimization.

🤝 Contributing

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

📜 License

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

🙏 Acknowledgments

Special thanks to all contributors and the deep learning community for inspiring this repository. Happy learning! 🎉