NOTE: This section is autogenerated by readme_ation.py, manual updates will be overwritten

This project involves building a neural network from scratch inspired by Andrej Karpathy's video "The spelled-out intro to neural networks and backpropagation: building micrograd". The primary goal was to deepen my understanding of neural networks, backpropagation, and gradient descent by implementing these concepts manually.

Prior to pursuing my master's in ML/AI, my knowledge was primarily derived from several Coursera courses on machine learning and readings from Twitter. I sought a practical project to solidify this theoretical foundation. Karpathy's tutorial provided an excellent starting point due to his expertise and clear explanations.

• Python: Core programming language.
• NumPy: For numerical operations and data handling.
• Graphviz: For visualizing neural networks, weights, and gradients.

1. Learning by Doing: Followed Karpathy’s tutorial, then independently implemented and expanded upon his concepts.
2. Extended Operations: Added additional operations such as tanh to the neural network.
3. Commenting and Documentation: Emphasized writing clear comments to aid future understanding and reinforce learning.
4. Custom Neuron Objects: Implemented a Neuron class to simulate action potentials, though later realized ReLU serves this purpose in traditional neural networks.

• Labeling System: Attempted to implement a comprehensive labeling system, which proved impractical for larger networks.
• Understanding ReLU: Initially misunderstood the role of ReLU, leading to an unnecessary Neuron class.
• Practical Application: Applied the network to a Kaggle competition task, achieving 55% accuracy (basically chance), highlighting the need for further refinement and understanding.

• Hands-On Experience: Building a neural network from scratch provided deep insights into the mechanics of neural networks.
• Importance of Iteration: Recognized the importance of iterative learning and continuous improvement.
• Foundation for Future Projects: The experience laid a solid foundation for more complex machine learning projects.

Special thanks to Andrej Karpathy for his invaluable tutorial, which guided the development of this project.

NOTE: This section is autogenerated by readme_ation.py, manual updates will be overwritten

This will guide you through the process of setting up a Mamba environment and running the provided Python code to see it in action. It uses the last known working versions of Python and packages used.

Ensure you have Mamba installed on your system. Mamba is a fast, cross-platform package manager.

1. Create a Mamba Environment

   Open your terminal and execute the following commands:

   mamba create -n myenv python=3.9.19 -y
   mamba activate myenv
   

2. Install Necessary Packages

   # Install each with mamba and fall back to pip if necessary
   for pkg in graphviz=2.50.0, numpy=1.26.4, readme_ation=0.1.12; do mamba install $pkg -y || pip install $pkg; done
   

3. Run the Script

   Ensure you are in your project directory and run the file you added the readme-ation code to and run:

   python [FILE_NAME]
   
   Or click 'run' in your IDE of choice.
   
   <!-- END SETUP AND RUN INSTRUCTIONS -->