10/20/23: HuggingFace lab day

 

 Machine Learning Study Group

Welcome! We start at 4:00, and go for 40 minutes. New members are always welcome and anyone can join. You may attend any or all sessions. Feel free to ask to be removed from the invite list at any time, as we have no wish to send unneeded emails which we all certainly get too many.

 

Agenda & Minutes

 

Welcome to the 85th meeting, Oct. 20, 2023!

• We are in "week" 3 of the 3-week quasi-cycle (which consists of reading in week 1, and HuggingFace labs in weeks 2 and 3, interspersed with weeks with other activities that happen from time to time). This means we will do a Huggingface lab.  
  

• To continue with the HuggingFace lab program, we did question answering today for week 3 of the cycle. See chapter 1,  part 3, https://huggingface.co/learn/nlp-course/chapter1/3?fw=tf. We will read about it briefly and then trying it in the running code window.
  

• Readings: We will discuss the top ranked item from the page of evaluated items next time we do readings.

• Next time PT will present a preliminary graph obtained from his LSTM model of time series prediction. 

• Announcement:
  

 -------------------------------------------------------------------

2nd OAK Supercomputing Conference

2 FREE Workshops and the 2nd OAK Supercomputing Conference
Oct 24-26, Little Rock AR
Contact: director-hpcc@okstate.edu
https://oak23.astate.edu

DETAILS:

The semi-annual OAK Supercomputing Conference is being hosted
by Arkansas State University.

Join us in Downtown Little Rock next week (Oct. 24-26).

Visit

https://oak23.astate.edu

for details.

Two VIRTUAL workshops are being organized as a part of this
conference.

These two workshops are available to ALL faculty, researchers,
post-doc and graduate students from Oklahoma, Arkansas and
Kansas (OAK) region.

YOU DO NOT NEED TO ATTEND THE CONFERENCE TO PARTICIPATE IN
THESE WORKSHOPS!

Oct. 24th, Virtual Workshop (Offered by NVIDIA):
Fundamentals of Deep Learning

Description: In this workshop, you'll learn how deep learning
works through hands-on exercises in computer vision and
natural language processing.

You'll train deep learning models from scratch, learning tools
and tricks to achieve highly accurate results.

You'll also learn to leverage freely available, state-of-the-
art pre-trained models to save time and get your deep learning
application up and running quickly.

More details on NVIDIA's website:

https://www.nvidia.com/en-us/training/instructor-led-workshops/fundamentals-of-deep-learning/

Offered by: Sri Koundinyan (from NVIDIA)
Cost: $0

Visit for details and registration:

https://hpcc.okstate.edu/nvidia-ml-workshop.html

Limit: Limited to first 50 participants