uttejh / DeepLearning_PyTorch

My projects and exercises for the latest Deep Learning ND program from Udacity

Home Page:https://www.udacity.com/course/deep-learning-nanodegree--nd101

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Deep Learning with PyTorch

This repository contains material related to Udacity's Deep Learning Nanodegree program. It consists of a bunch of notebooks for various deep learning topics.

Built With

  • PyTorch
  • Python 3
  • Google Colab

Table Of Contents

Introduction to Neural Networks

  • Introduction to Neural Networks: implemented gradient descent and applied it to predicting patterns in student admissions data.
  • Sentiment Analysis with NumPy: built sentiment analysis model, predicting if some text is positive or negative.
  • Introduction to PyTorch: built neural networks in PyTorch and used pre-trained networks for state-of-the-art image classifiers.

Convolutional Neural Networks

  • Convolutional Neural Networks: Visualized the output of layers that make up a CNN. Defined and train a CNN for classifying MNIST data, a handwritten digit database that is notorious in the fields of machine and deep learning. Also, defined and trained a CNN for classifying images in the CIFAR10 dataset.
  • Transfer Learning: used VGGnet to help classify images of flowers without training an end-to-end network from scratch.
  • Weight Initialization: Explore how initializing network weights affects performance.
  • Style Transfer: Extract style and content features from images, using a pre-trained network. Implemented style transfer according to the paper, Image Style Transfer Using Convolutional Neural Networks by Gatys et. al. Defined appropriate losses for iteratively creating a target, style-transferred image of your own design

Recurrent Neural Networks

  • Intro to Recurrent Networks (Time series & Character-level RNN): implemented RNN in PyTorch for a variety of tasks.
  • Embeddings (Word2Vec): Implemented the Word2Vec model to find semantic representations of words for use in natural language processing.
  • Sentiment Analysis RNN: Implemented a recurrent neural network that can predict if the text of a moview review is positive or negative.

Deploying a Model (with AWS SageMaker)

  • Learnt to deploy pre-trained models using AWS SageMaker.

TODO

  • GAN (Generative Adversarial Networks)
  • Projects

  • Predicting Bike-Sharing Patterns
  • Face Generation
  • TV Script Generation
  • Dog Breed Classifier

Acknowledgements

  • Udacity Deep Learning Nano Degree Program

About

My projects and exercises for the latest Deep Learning ND program from Udacity

https://www.udacity.com/course/deep-learning-nanodegree--nd101


Languages

Language:Jupyter Notebook 100.0%