Nonlinear spectral preprocessing for small-brain machine learning

Luat T. Vuong; Hobson Lane

doi:10.1117/12.2530789

6 September 2019 Nonlinear spectral preprocessing for small-brain machine learning

Luat T. Vuong, Hobson Lane

Proceedings Volume 11139, Applications of Machine Learning; 111390T (2019) https://doi.org/10.1117/12.2530789
Event: SPIE Optical Engineering + Applications, 2019, San Diego, California, United States

Abstract

Substantial computing costs are required to use deep-learning algorithms. Here, we implement feature extraction based on analytic relations in the Fourier-transform domain. In an example relevant to visual odometry, we demonstrate a reduction in algorithmic complexity with cross-power spectral preprocessors for feature extraction in lieu of learned convolutional filters. With spectral reparameterization and spectral pooling, not only can the optical flow (spatial disparity of images in a sequence) be computed, but occluding objects can also be tracked in the foreground without deep learning. There is evidence that insects with small brains implement similar visual-data spectral preprocessors, which may be critical in the development of future real-time machine learning applications.

Citation Download Citation

Luat T. Vuong and Hobson Lane "Nonlinear spectral preprocessing for small-brain machine learning", Proc. SPIE 11139, Applications of Machine Learning, 111390T (6 September 2019); https://doi.org/10.1117/12.2530789

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