Relating information complexity and training in deep neural networks

Alex Gain; Hava Siegelmann

doi:10.1117/12.2520172

13 May 2019 Relating information complexity and training in deep neural networks

Alex Gain, Hava Siegelmann

Proceedings Volume 10982, Micro- and Nanotechnology Sensors, Systems, and Applications XI; 109822H (2019) https://doi.org/10.1117/12.2520172
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Deep Neural Networks may be costly to train, and if testing error is too large, retraining may be required, unless lifelong learning methods are applied. Crucial to addressing learning at the edge, without access to powerful cloud computing, is the notion of problem difficulty for non-standard data domains. While it is known that training is harder for classes that are more entangled, the complexity of data points was not previously studied as an important contributor to training dynamics. We analyze data points by their information complexity and relate the complexity of the data to the test error. We elucidate training dynamics of DNNs, demonstrating that high complexity datapoints contribute to the error of the network, and that training DNNs consist of two important aspects - (1) Minimization of error due to high complexity datapoints, and (2) Margin decrease where entanglement of classes occurs. Whereas data complexity may be ignored when training in a cloud, it must be considered as part of the setting when training at the edge.

Citation Download Citation

Alex Gain and Hava Siegelmann "Relating information complexity and training in deep neural networks", Proc. SPIE 10982, Micro- and Nanotechnology Sensors, Systems, and Applications XI, 109822H (13 May 2019); https://doi.org/10.1117/12.2520172

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available