Deep-Learning

Deep Learning Projects Repository

Welcome to the Deep Learning Projects Repository! This repository contains a collection of Jupyter notebooks and scripts demonstrating various deep learning techniques and applications using Python. Each project focuses on a different aspect of deep learning, providing a broad overview of the field.

Table of Contents

1. Artificial Neural Networks (ANN)
2. Convolutional Neural Networks (CNN)
3. Recurrent Neural Networks (RNN)
4. Generative Adversarial Networks (GAN)
5. Bag of Words
6. Linear and Multiple Regression with ANN
7. Logic Gates using ANN
8. Movie Review Sentiment Analysis (IMDB)

Project Descriptions

Artificial Neural Networks (ANN)

• Notebooks:
  • ANN_Breast_Cancer.ipynb
  • ANN_Churn.ipynb
  • ANN_Iris_Classification.ipynb
  • ANN_Tips_Regression.ipynb
  • Bike_Sharing_ANN_Regression.ipynb
• Description: These notebooks cover various applications of artificial neural networks (ANNs) including classification and regression tasks using different datasets such as breast cancer, customer churn, iris classification, tips, and bike sharing demand.

Bag of Words

• Scripts:
  • Bag_of_words_COUNT.ipynb
  • Bag_of_words_FILE.ipynb
• Description: The scripts preprocess text data by tokenizing, removing stopwords, and punctuation, and storing unique words. They also create a bag-of-words representation and display word frequency counts, which are fundamental techniques in natural language processing (NLP).

Convolutional Neural Networks (CNN)

• Notebook:
  • CNN_Cat_Dog.ipynb
  • CNN_Dog_Breed.ipynb
  • CNN_Monkey_Breed.ipynb
  • Rock_Paper_Scissor.ipynb
• Description: This notebook demonstrates the use of convolutional neural networks (CNNs) for image classification tasks. It covers data preprocessing, model building, training, and evaluation using a popular image dataset.

Recurrent Neural Networks (RNN)

• Notebooks:
  • RNN_Time_Series.ipynb
  • RNN_Number_series_prediction.ipynb
  • RNN_Monthly_Milk_Production.ipynb
  • RNN_Energy_Consumption.ipynb
• Description: These notebooks showcase the application of recurrent neural networks (RNNs) using SimpleRNN or LSTM layers for various time series and sequence prediction tasks including bike sharing demand, number series, monthly milk production, and energy consumption.

Generative Adversarial Networks (GAN)

• Notebook: GAN.ipynb
• Description: This notebook introduces Generative Adversarial Networks (GANs) and demonstrates how they can be used to generate new data samples that resemble a given dataset. It covers the architecture of GANs, model training, and evaluation.

Linear and Multiple Regression with ANN

• Notebook: Linear_and_Multiple_Regression_ANN.ipynb
• Description: This notebook applies artificial neural networks to perform linear and multiple regression tasks. It provides a comparison with traditional regression techniques and highlights the advantages of using ANNs for such problems.

Logic Gates

• Notebook: Logic_Gates.ipynb
• Description: This notebook demonstrates how to use artificial neural networks to simulate basic logic gates such as AND, OR, and XOR. It serves as an introductory project to understand the working of ANNs.

Movie Review Sentiment Analysis (IMDB)

• Notebook: Movie_Review_IMDB.ipynb
• Description: This notebook uses deep learning techniques to perform sentiment analysis on movie reviews from the IMDB dataset. It covers data preprocessing, model building, training, and evaluation for classifying reviews as positive or negative.