Skip to main content

Regularized Deep Learning with Data Geometry and Filter Structures

Qiang Qiu, PhD. Assistant Professor Department of Electrical and Computer Engineering, Duke University

Event Details

Date
Tuesday, February 18, 2020
Time
12-1 p.m.
Description
The central problem of deep learning is how to generalize well from training data to unseen data. One such solution is to regularize deep learning with priors encoded into models. In this talk we will discuss various techniques we
recently developed in regularizing deep learning with data geometry, such as lowrank subspace, or structures over convolutional filters.
Cost
Free

Tags