---

Neural Network and Deep Learning (NNDL) Projects

This repository contains assignments and experiments I completed as part of my studies in Neural Networks and Deep Learning. Each project focuses on different aspects of deep learning, including classification, prediction, and model development using various neural network architectures.

Project Structure

File	Description
1_ANN_Model(XOR_GATE).ipynb	Experiment 1: Implemented an Artificial Neural Network (ANN) for XOR Gate classification.
2_Deep_Learning_Model_(Telecom_company_data).ipynb	Experiment 2: Built a deep learning model for customer churn prediction using telecom company data.
3_Churn_Prediction(Bank_Dataset).ipynb	Experiment 2 (Homework): Developed a churn prediction model using a bank dataset.
4_CNN_Classification_(Handwritten_digits).ipynb	Experiment 3: Implemented a Convolutional Neural Network (CNN) for handwritten digit classification.
5_CNN_Image_Classification(CIFAR10).ipynb	Experiment 3 (Homework): Applied CNN for image classification on the CIFAR-10 dataset.
6_RNN_LSTM_(milk_production_prediction).ipynb	LSTM: Created a Recurrent Neural Network (RNN) with LSTM cells for milk production prediction.
7_Training_&_Testing_Data(BMW_Dataset).ipynb	Linear Regression: Performed training and testing on the BMW dataset using linear regression.
8_Simple_AutoEncoder.ipynb	Deep Learning: Implemented a simple autoencoder for unsupervised feature learning.

Repository Details

Each file contains code for setting up, training, and evaluating various neural network models on specific datasets. These projects demonstrate techniques for tasks such as:

• Binary classification with ANNs.
• Customer churn prediction using deep learning models.
• Image classification with CNNs on popular datasets like CIFAR-10.
• Time-series prediction using LSTM-based RNNs.
• Feature extraction with autoencoders.

Getting Started

To run any of these notebooks, ensure you have the necessary Python packages installed. A typical environment setup may include the following packages:

• numpy
• pandas
• tensorflow or keras
• matplotlib
• scikit-learn

You can install them with the following command:

pip install numpy pandas tensorflow matplotlib scikit-learn

Usage

1. Clone the repository:

   git clone https://github.com/Tanishqa-10/NNDL-projects.git

2. Navigate to the project folder and open any Jupyter Notebook file:

   jupyter notebook <notebook_name>.ipynb

3. Run each cell sequentially to train and evaluate the models.