Udacity-Projects

I enrolled for Deep Learning Nanodegree course from Udacity.These projects i created from what i learnt from Udacity. Checkout these projects and if you want to make your own do fork , clone and start experimenting. :D

Bike-Sharing prediction

In this project i build Neural network that to carry out a prediction problem on a real dataset! It is used to predict daily bike rental ridership. Applied Gradient Decent, Backpropagation concepts from sratch. The data comes from the UCI Machine Learning Database

The training loss is below 0.09 and the validation loss is below 0.18.

Predictaion Here, used the test data to view how well my network is modeling the data

Dog Breed Classifer

This is Convolutional Neural Networks (CNN) project! In this project,.Given an image of a dog, algorithm will identify an estimate of the canine’s breed. If supplied an image of a human, the code will identify the resembling dog breed. For this project i used VGG16 model. The accuracy on test data Test Loss: 0.959668 Test Accuracy: 73% (615/836)

TV Script Generation using RNN

In this project , i generated own Seinfeld TV scripts using RNNs.I used some part of the Seinfeld dataset of scripts from 9 seasons. The Neural Network generated a new ,"fake" TV script, based on patterns it recognizes in this training data. The RNN included an LSTM and one fully-connected layer.

Face Generation

In this project i used used generative adversarial networks (GANs) to generate new images of faces. I trained a [DCGAN] (https://arxiv.org/abs/1511.06434) on a dataset of faces.The goal was to get a generator network to generate new images of faces that look as realistic as possible! I used CelebFaces Attributes Dataset (CelebA) to train adversarial networks.