TensorFlow & PyTorch User Group

The deep learning research community at Princeton comprises over 10 academic departments and more than 200 researchers. The TensorFlow and PyTorch User Group was created to serve as a campus-wide platform for researchers to connect with one another to discuss their work and the use of the tools. In addition to monthly presentations by graduate students and postdoctoral researchers, the group hosts external speakers from such companies as Google, NVIDIA and Intel. All members of the PU research community are welcome. Subscribe to the mailing list.

    Getting Started Guide on TensorFlow at Princeton
    Getting Started Guide on PyTorch at Princeton

The group is sponsored by the Princeton Institute for Computational Science and Engineering (PICSciE) and the Center for Statistics and Machine Learning (CSML).


Next Meeting

Wednesday, February 26 at 4:30-6:30 pm
138 Lewis Science Library
Foundations of Deep Learning with PyTorch

CLICK HERE TO RSVP

Of the many deep learning frameworks, PyTorch has largely emerged as the first choice for researchers. This workshop will show participants how to implement and train common network architectures in PyTorch. Special topics will be included as time permits. Participants should have some knowledge of Python, NumPy and deep learning theory. Bring a laptop if you would like to do the hands-on exercises and follow the installation instructions at https://github.com/Atcold/pytorch-Deep-Learning-Minicourse.

Alternatively, you can use Binder or Google Colab to run the notebooks in the cloud. Feel free to arrive at the end of the workshop for one-on-one discussions with Alf about advanced PyTorch topics and the direction of the framework. Also, you can follow up on Twitter using the handle @alfcnz

Speaker: Alfredo Canziani is an Assistant Professor of Computer Science and a Deep Learning Research Scientist at NYU Courant, Institute of Mathematical Sciences, in the research group of AI pioneer Yann LeCun. Alf contributes and works directly with the PyTorch developers at Facebook in NYC. His research work is concerned with model predictive policy learning for autonomous vehicles.

This workshop was organized by the TensorFlow & PyTorch User Group. It is sponsored by the Princeton Institute for Computational Science and Engineering (PICSciE) and the Center for Statistics and Machine Learning (CSML).


Upcoming meeting

Wednesday, March 25 at 4:30-6:00 pm
138 Lewis Science Library

Diving to TensorFlow 2.0

CLICK HERE TO RSVP

Please join us for this 90-minute workshop, taught at an intermediate level. We will briefly introduce TensorFlow, then dive into writing two flavors of neural networks (DNNs and CNNs). Attendees will need a laptop and an internet connection. There is nothing to install in advance, we will use https://colab.research.google.com for examples. We will start with MNIST, then proceed to training a model to recognize cats and dogs. We will finish with a brief intro to a couple more advanced examples to visualize the features learned by a CNN (including Attention Maps, Style Transfer, and Deep Dream). If there's anything you'd like to chat about in more depth, Josh will be around afterwards to speak 1:1.

Speaker: Josh Gordon works on the TensorFlow team at Google, and teaches Applied Deep Learning at Columbia. You can find him online at https://twitter.com/random_forests

This workshop was organized by the TensorFlow & PyTorch User Group. It is sponsored by the Princeton Institute for Computational Science and Engineering (PICSciE) and the Center for Statistics and Machine Learning (CSML).


Previous meetings

NOVEMber 2019

A Dive in to TensorFlow 2.0 by Josh Gordon

October 2019

Leveraging Intel Software Libraries for Accelerated AI Research by Jonathan Halverson
Continual adaptation for efficient machine communication by Robert D. Hawkins
Accelerating automated modeling and design with stochastic optimization and neural networks by Alex Beatson

September 2019

JAX: Accelerated machine learning research via composable function transformations in Python by Peter Hawkins

 

July 2019

Selene: A PyTorch-based Deep Learning Library for Sequence Data by Kathleen Chen
Big data of big tissues: deep neural networks to accelerate analysis of collective cell behaviors in large populations by Julienne LaChance
GPU Computing with R and Keras by Danny Simpson
Announcements and TensorFlow 2 (beta) by Jonathan Halverson

 

June 2019

Opportunities and challenges in self-driving cars at NVIDIA by Timur Rvachov (slides not available)
Training deep convolutional neural networks by Michael Churchill
Deep Learning Frameworks at Princeton by Jonathan Halverson

 

 

Contact

For more information please contact Jonathan Halverson (halverson@princeton.edu)

 
Kathleen Chen at Princeton