BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//RLASKEY//CALENDEROUS//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260914T140952Z
LAST-MODIFIED:20210306T015924Z
DTSTART:20210308T200000Z
DTEND:20210308T210000Z
UID:event2410@bu.edu
URL:http://physics.bu.edu/internal/events/show/2410
SUMMARY:Predicting nucleation using machine learning in the Ising model
DESCRIPTION:Featuring Shan Huang\, Boston University\, Physics Department\n
	\nPart of the Departmental Seminars.\n\nWe use a convolutional neural netwo
	rk (CNN) and two logistic regression models to predict the probability of n
	ucleation in the two-dimensional Ising model. The three methods successfull
	y predict the probability for the nearest-neighbor Ising model for which cl
	assical nucleation is observed. The CNN outperforms the logistic regression
	 models near the spinodal of the long-range Ising model\, but the accuracy 
	of its predictions decreases as the quenches approach the spinodal. An occl
	usion analysis suggests that this decrease is due to the vanishing differen
	ce between the density of the nucleating droplet and the background. Our re
	sults are consistent with the general conclusion that predictability decrea
	ses near a critical point.
LOCATION: \, \, 
STATUS:CONFIRMED
CLASS:PUBLIC
END:VEVENT
END:VCALENDAR