BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Academics,Academic Seminar,Virtual
DESCRIPTION:Mathematics Colloquim\n\nSpeaker: Dr. Zerotti Woods\, Johns
Hopkins University\n\nAbstract: In this work\, we present a new regular
ization term that penalizes the conditioning of the weight matrices in a de
ep neural network. We give a mathematical argument that suggests that in c
ertain situations\, the conditioning number of the weight matrices have a d
irect impact on the error in classification. Empirical evidence suggests t
hat improving the weight matrix associated with the output layer of a matri
x improves generalizability when classifying ECG data from a benchmark data
-set\, and also a novel malaria infection data-set.
DTEND:20210416T190000Z
DTSTAMP:20230928T181317Z
DTSTART:20210416T180000Z
LOCATION:
SEQUENCE:0
SUMMARY:A New Regularization Term for Deep Neural Networks With Application
s to Biological Data - VIRTUAL
UID:tag:localist.com\,2008:EventInstance_36448868019809
URL:https://events.towson.edu/event/a_new_regularization_term_for_deep_neur
al_networks_with_applications_to_biological_data_-_virtual
END:VEVENT
END:VCALENDAR