BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//RLASKEY//CALENDEROUS//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20261017T111441Z
LAST-MODIFIED:20161025T061342Z
DTSTART:20161027T193000Z
DTEND:20161027T203000Z
UID:event1669@bu.edu
URL:http://physics.bu.edu/internal/events/show/1669
SUMMARY:Analyzing LArTPC Images Using Deep Learning
DESCRIPTION:Featuring Kazuhiro Terao\, Columbia University\nHosted by: Chri
	stopher Grant\n\nPart of the HEE Seminar Series.\n\nDeep Learning\, a machi
	ne learning algorithm using convolutional neural networks (CNNs)\, is the s
	tate-of-the-art technique in the field of artificial intelligence\, in part
	icular computer vision.  Deep learning has found a vast number of applicati
	ons ranging from automated human face recognition\, real-time object detect
	ion for self-driving cars\, teaching a robot Chinese\, and even playing Go.
	 In this talk\, we present our first steps in exploring the use of Deep Lea
	rning to the task of analyzing neutrino events coming from Liquid Argon Tim
	e Projection Chambers (LArTPC)\, in particular the MicroBooNE detector. LAr
	TPCs consist of a large volume of liquid argon sandwiched between a cathode
	 and anode wire planes.  These detectors are capable of recording images of
	 charged particle tracks with breathtaking resolution.  Such detailed infor
	mation will allow LArTPCs to perform accurate particle identification and c
	alorimetry\, making it the detector of choice for many current and future n
	eutrino experiments.  However\, analyzing such images can be challenging\, 
	requiring the development of many algorithms to identify and assemble featu
	res of the events in order to identify and remove cosmic-ray-induced partic
	les and reconstruct neutrino interactions. I present our current status of 
	applying CNN techniques to analyze LArTPC images\, and show the current per
	formance of these networks on performing particle identification and neutri
	no interaction identification and localization.
LOCATION:PRB 595\, 3 Cummington Mall\, 02215
STATUS:CONFIRMED
CLASS:PUBLIC
END:VEVENT
END:VCALENDAR