Fermilab Computing Division

HEP Software R&D at Frontier of Data Science and Deep Learning

Simple document list
(1 extra document)

Full Title: HEP Software R&D at Frontier of Data Science and Deep Learning
Date & Time: 18 Dec 2015 at 13:00
Event Location: WH1W
Event Topic(s): Computing Techniques Seminar
Event Moderator(s):
Event Info: Speaker:
Amir Farbin

In the next decade, the frontiers of High Energy Physics (HEP) will be explored by three machines: the High Luminosity Large Hadron Collider (HL-LHC) in Europe, the Long Base Neutrino Facility (LBNF) in the US, and the International Linear Collider (ILC) in Japan. These next generation experiments must address two fundamental problems in the current generation of HEP experimental software: the inability to take advantage and adapt to the rapidly evolving processor landscape, and the difficulty in developing and maintaining increasingly complex software systems by physicists. I will first speculate on how techniques and tools from Data Science and Deep Learning may help alleviate these issues. I will then present a simple demonstration of Deep Neural Network event classification using raw data from Liquid Argon Time Projection Chambers (LArTPC) experiments and present a roadmap towards DNN full event reconstruction. Finally I will discuss how representing data as Tensors and using Direct Acyclic Graph optimization techniques, as done in Deep Learning software such as Theano and TensorFlow, could alleviate HEP software challenges in future HEP software frameworks.

No talks in agenda

Other documents for this event

CS-doc-# Title Author(s) Topic(s) Last Updated
5662-v1 HEP Software R&D at Frontier of Data Science and Deep Learning - - Experiment/Scientific Program
High Performance Computing
18 Dec 2015

DocDB Home ]  [ Search ] [ Authors ] [ Events ] [ Topics ]

DocDB Version 8.8.9, contact Document Database Administrators
Execution time: 0 wallclock secs ( 0.16 usr + 0.03 sys = 0.19 CPU)