PyTorch Scholarship Challenge
Written by Sue Gee   
Thursday, 04 October 2018

A partnership between Facebook and Udacity has resulted in 10,000 challenge seats being made available in a new Udacity course “Introduction to Deep Learning with PyTorch,” built in collaboration with Soumith Chintala, Facebook AI Researcher and the creator of PyTorch.

After the two-month challenge course, three hundred students will earn a full scholarship from Facebook to Udacity’s Deep Learning Nanodegree, which is the four-month program that costs $999 that we've previous reported on.

PYTORCHBANNER

News of this opportunity was announced at the inaugural PyTorch Developer Conference, which saw the release of the open source AI framework PyTorch 1.0 in developer preview and also fastai 1.0, an open-source deep learning library built on top of PyTorch.

The PyTorch Scholarship Challenge is structured in two phases: 

  • Phase 1 is the Challenge Course. The duration of this new course, “Introduction to Deep Learning with PyTorch” is two months during which program participants will receive support from community managers.

  • In Phase 2, the top 300 students in terms of output and collaboration from the first phase will earn full scholarships to Udacity’s Deep Learning Nanodegree program, where they’ll cover topics such as: Convolutional and Recurrent Neural Networks, Generative Adversarial Networks, Deployment, and more. Students will use PyTorch, and have access to GPUs to train models faster, as they learn from authorities like Sebastian Thrun, Ian Goodfellow, Jun-Yan Zhu, and Andrew Trask. 

The pre-requisites for the PyTorch Scholarship Challenge are intermediate Python programming experience and linear algebra. It is open to applicants aged 18 and over and as well as providing background information and answering questions to establish your familiarity with Python, calculus, linear algebra and Numpy you need to provide short paragraphs outlining: 

  • What do you hope to accomplish through this program?

and  

  • Why should you receive a scholarship?

The terms of the scholarship whereby fees for the Nanodegree Program will be fully covered by Facebook, the Scholarship Sponsor, and Udacity include the proviso that Udacity may share updates and data on recipients' progress in the Nanodegree Program with Facebook and that names and images may be announced publicly and used to promote the scholarship program. Information provided in the application may be used for future scholarship opportunities and that this may include sharing information with potential scholarship sponsors.

Introduction to Deep Learning with PyTorch consists of eight lessons:

1 - Introduction to Deep Learning

  • Discover the basic concepts of deep learning such as neural networks and gradient descent
  • Implement a neural network in NumPy and train it using gradient descent with in-class programming exercises
  • Build a neural network to predict student admissions

2 - Introduction to PyTorch

  • Hear from Soumith Chintala, the creator of PyTorch, how the framework came to be, where it’s being used now, and how it’s changing the future of deep learning

3 - Deep Learning with PyTorch

  • Build your first neural network with PyTorch to classify images of clothing
  • Work through a set of Jupyter Notebooks to learn the major components of PyTorch
  • Load a pre-trained neural network to build a state-of-the-art image classifier

4 - Convolutional Neural Networks

  • Use PyTorch to build Convolutional Neural Networks for state-of-the-art computer vision applications
  • Train a convolutional network to classify dog breeds from images of dogs

5 - Style Transfer

  • Use a pre-trained convolutional network to create new art by merging the style of one image with the content of another image
  • Implement the paper "A Neural Algorithm of Artistic Style” by Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge"

6 - Recurrent Neural Networks

  • Build recurrent neural networks with PyTorch that can learn from sequential data such as natural language
  • Implement a network that learns from Tolstoy’s Anna Karenina to generate new text based on the novel

 

7  - Natural Language Classification

  • Use PyTorch to implement a recurrent neural network that can classify text
  • Use your network to predict the sentiment of movie reviews

8 - Deploying with PyTorch

  • Soumith Chintala teaches you how to deploy deep learning models with PyTorch
  • Build a chatbot and compile the network for deployment in a production environment

For anyone interested in deep learning this sounds like a great free course.  

PYTORCHSQ

More Information

PyTorch Scholarship Challenge from Facebook

Deep Learning Nanodegree

Introduction to Deep Learning with PyTorch 

Related Articles

Deep Learning From Udacity and Coursera 

Udacity Announces School of AI

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Banner


CSS Ecosystem In the Spotlight
06/11/2024

The 2024 edition of the State of CSS has been posted, revealing that the latest features of the language not only do away with extra tooling, but even start taking on tasks that previously requir [ ... ]



OpenAI Library For .NET Exits Beta
19/11/2024

A few months ago the OpenAI .NET library was released as a beta. It has now reached version 2.0.0 and the time has come to leave beta and, with a few amendments enter production readiness.


More News

espbook

 

Comments




or email your comment to: comments@i-programmer.info

 

Last Updated ( Friday, 03 May 2019 )