DATE:

Friday, February 21, 2020

TIME:

3:00 PM

LOCATION:

GMCS-314

SPEAKER:

Dr. Victor Pereyra, Consulting Professor, Stanford University

ABSTRACT:

Under the premise that less is better we consider the design of Deep Neural Networks with several twists to reduce the number of unknown parameters for a given accuracy. This is good fitting practice but it is also required for deployment in small platforms, such as phones and watches.

HOST:

Jose Castillo

DOWNLOAD: