DeepLearning

This repository includes projects completed as a part of Deep Learning Nanodegree program. It starts with building a simple neural network to building a generative adversarial networks (GANs) to generate realistic faces.

1. Bike Share Neural Network

This is the first project completed in the nanodegree program where we use bike share data set and build a prediction model using a neural network to predict the number of bike share users on any given day.

2. Sentiment Analysis with Andrew Trask

This project is based on lectures by Andrew Trask on sentiment analysis and contains step-by-step introduction to sentiment analysis using IMDB movie reviews dataset.

3. Image Classification CIFAR-10

The project implements a convolutional neural network on CIFAR-10 dataset which contains images from 10 different categories.

4. TV Script Generation

In this project we implement a recurrent neural network to generate TV script. We use part of the Simpsons dataset of scripts from 27 seasons. The recurrent neural network generates a new TV script for a scene at Moe's Tavern.

5. Language Translation

The project uses a sequence to sequence model on a dataset of English and French sentences that can translate new sentences from English to French.

6. Face Generation

The project uses a generative adversarial networks to generate new images of faces.