Grainger College of Engineering, All Events

View Full Calendar

NCSA-NVIDIA AI Hackathon II - Sign-Up

Event Type
Other
Sponsor
NCSA-NVIDIA
Date
Nov 5, 2019   8:30 am  
Views
14
Originating Calendar
Illinois ECE Calendar

The second NCSA-NVIDIA AI Hackathon of the semester is co-organized by the Gravity GroupInnovative Systems Lab, and NCSA Industry, and co-sponsored by NCSA SPIN and NVIDIA. The main goal of the hackathon is to let talented U of I students, postdocs and staff showcase their skills in a friendly competition while working on challenging problems involving deep learning on a state-of-the-art compute platform designed for AI. This will be an intensive 2-day experience culminating in the final presentation of results on Sunday afternoon. Courtesy of NVIDIA, the winning team will receive two Titan V GPU cards. The second-place team will receive one Titan V GPU card.

To participate, we ask interested students and staff to sign up at https://forms.illinois.edu/sec/7957390 by Tuesday, November 5 and indicate which of the three projects described below they would like to work on. Students accepted to participate in the event will be notified on Thursday, November 7.

PROJECT 1: FALL DETECTION WITH DEEP NEURAL NETS

Problem: Develop a model to perform human activity recognition, specifically to detect falls. Falls are an important health problem worldwide and reliable automatic fall detection systems can play an important role to mitigate negative consequences of falls. For more details, refer to https://wiki.illinois.edu/wiki/display/~kindrtnk/Fall+detection.

Datasets: Data will be provided at the time of the competition on HAL cluster.

PROJECT 2: SEMANTIC AMODAL SEGMENTATION

Problem: Train a model to perform amodal segmentation of humans. Results will be evaluated on accuracy of predicted regions that describe visible and occluded human body parts. For more details, refer to sailvos.web.illinois.edu.

Datasets: Data will be provided at the time of the competition on HAL cluster.

PROJECT 3: FEATURE RECOGNITION IN DIGITAL ELEVATION MAPS

Problem: Develop and train a model to recognize features in Digital Elevation Maps (DEMs). The provided dataset contains pre-processed DEM tiles with labeled regions of interests. The features of interest are soil erosion regions. More details, refer to https://wiki.illinois.edu/wiki/display/~kindrtnk/DEMs.

Datasets: Data will be provided at the time of the competition on HAL cluster.

Related Link: NCSA-NVIDIA AI Hackathon II

link for robots only