Deep Learning using neural networks

This repository contains deep learning projects, completed as part of course work for Artificial Intelligence Nanodegree with Udacity in 2017.

Dog Breed Classifier

This notebook makes the first steps towards developing an algorithm that could be used as part of a mobile or web app. The code implements a Convolutional Neural Network using Keras over Tensorflow. The code will accept any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed. If a human is detected, it will provide an estimate of the dog breed that is most resembling.

RNN Project

This notebook contains a variety of tasks solving 2 problems- Time Series and Sequence Generation, using a Recurrent Neural Network architecture of type LSTM(Long Term Short Memory.) It is divided as a list of tasks:-

1. Implement a function to window time series
2. Create a simple RNN model using keras to perform regression
3. Finish cleaning a large text corpus
4. Implement a function to window a large text corpus
5. Create a simple RNN model using keras to perform multiclass classification
6. Generate text using a fully trained RNN model and a variety of input sequences