Neural Network Notebooks

This repository contains the lab works from the Neural Network and Fuzzy Logic course at Rajshahi University of Engineering & Technology (RUET). The notebooks implement various neural network algorithms and showcase practical applications of machine learning models.

🧠 Neural Network Algorithms Implemented:

• K Nearest Neighbour (KNN): Implementation of KNN from scratch and comparison with built-in KNN models.
• Single Layer Perceptron: Implementation of a simple perceptron model for binary classification tasks.
• Multi-Layer Perceptron: A more advanced model involving multiple layers with backpropagation for training.

🔍 Key Files:

1. K Nearest Neighbour (KNN):

   • K Nearest Neighbour Scratch vs Built-In on Breast Cancer Dataset.ipynb: Comparison of KNN from scratch and built-in methods on the Breast Cancer dataset.
   • Implement K Nearest Neighbour From Scratch and Compare with the Built-in Graphically.ipynb: Visual comparison of custom vs built-in KNN.

2. Single Layer Perceptron:

   • Single Layer Perceptron.ipynb: Simple perceptron model to classify binary data.

3. Multi-Layer Perceptron (MLP):

   • Multi-Layer Perceptron & Backpropagation Binary Classifier.ipynb: Implementation of a multi-layer perceptron and backpropagation algorithm for binary classification.

4. Datasets:

   • Breast_Cancer_Dataset.csv: The dataset used for training and testing the KNN model.

🚀 How to Run the Project:

1. Clone the repository:

   git clone https://github.com/AudityGhosh/Neural_Network_Notebooks.git

2. Navigate to the directory:

   cd Neural_Network_Notebooks

3. Open the Jupyter notebooks:

   jupyter notebook

4. Run the notebooks in the order they appear to explore each neural network model.

🔗 References:

• Neural Computing - An Introduction: The book used as a reference for implementing various neural network models.
• Special Thanks: Gratitude to Kuldip Saha, classmate, and Nur E Anika Anan, senior, for their valuable support during the development of this project.

💬 Contributions:

Feel free to fork the repository, contribute to the projects, or suggest improvements. Pull requests are welcome!

---

This project was developed by Audity Ghosh as part of the Neural Network and Fuzzy Logic course at RUET, with special thanks to the authors and contributors.