Demystifying Deep Learning: a Geometric Approach to Iterative Projections
Paper in proceedings, 2018

Parametric approaches to Learning, such as deep learning (DL), are highly popular in nonlinear regression, in spite of their extremely difficult training with their increasing complexity (e.g. number of layers in DL). In this paper, we present an alternative semi-parametric framework which foregoes the ordinarily required feedback, by introducing the novel idea of geometric regularization. We show that certain deep learning techniques such as residual network (ResNet) architecture are closely related to our approach. Hence, our technique can be used to analyze these types of deep learning. Moreover, we present preliminary results which confirm that our approach can be easily trained to obtain complex structures.

Author

Ashkan Panahi

Chalmers, Computer Science and Engineering (Chalmers), Data Science

Hamid Krim

Liyi Dai

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

15206149 (ISSN)

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Calgary, Canada,

Subject Categories

Telecommunications

Probability Theory and Statistics

Signal Processing

DOI

10.1109/ICASSP.2018.8462687

More information

Latest update

11/1/2019