The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Workshop: EduHPC-23: Workshop on Education for High Performance Computing
Authors: Maria Pantoja (California Polytechnic State University, San Luis Obispo; Argonne National Laboratory (ANL)); Erik Pautsch (Loyola University, Chicago); John Li (University of California, San Diego (UCSD)); Silvio Rizzi (Argonne National Laboratory); and George Thiruvathukal (Loyola University, Chicago)
Abstract: Deep Learning (DL) methods have recently dominated the fields of Machine Learning. Most DL models assume that the input data distribution is identical between testing and validation, though they often are not. For example, if we train a traffic sign classifier, the model might confidently, but incorrectly, classify a graffitied stop sign as a speed limit sign. Often ML provides high-confidence (softmax) output for out-of-distribution input that should have been classified as "I don't know". By adding the capability of propagating uncertainty to our results, the model can provide not just a single prediction, but a distribution over predictions that will allow the user to determine the model's reliability and whether it needs to be deferred to a human expert. Uncertainty estimation is computationally expensive; in this assignment, we will learn to accelerate the calculations using common distributed systems divide and conquer techniques.
Files given to students (Slides&Code ) (link:\url{https://drive.google.com/drive/folders/1KrxWlMZpoJzph0Y7VbZj_yYyACK-Jusl?usp=sharing})
Back to EduHPC-23: Workshop on Education for High Performance Computing Archive Listing