Pooling networks for a discrimination task: noise-enhanced detection

Pierre-Olivier Amblard; Steeve Zozor; Mark D. McDonnell; Nigel G. Stocks

doi:10.1117/12.724641

15 June 2007 Pooling networks for a discrimination task: noise-enhanced detection

Pierre-Olivier Amblard, Steeve Zozor, Mark D. McDonnell, Nigel G. Stocks

Proceedings Volume 6602, Noise and Fluctuations in Biological, Biophysical, and Biomedical Systems; 66020S (2007) https://doi.org/10.1117/12.724641
Event: SPIE Fourth International Symposium on Fluctuations and Noise, 2007, Florence, Italy

Abstract

Pooling networks are composed of noisy independent neurons that all noisily process the same information in parallel. The output of each neuron is summed into a single output by a fusion center. In this paper we study such a network in a detection or discrimination task. It is shown that if the network is not properly matched to the symmetries of the detection problem, the internal noise may restore at least partially some kind of optimality. This is shown for both (i) noisy threshold model neurons, as well as (ii) Poisson neuron models. We also study an optimized version of the network, mimicking the notion of excitation/inhibition. We show that, when properly tuned, the network may reach optimality in a very robust way. Furthermore, we find in this optimization that some neurons remain inactive. The pattern of inactivity is organized in a strange branching structure, the meaning of which remains to be elucidated.

Citation Download Citation

Pierre-Olivier Amblard, Steeve Zozor, Mark D. McDonnell, and Nigel G. Stocks "Pooling networks for a discrimination task: noise-enhanced detection", Proc. SPIE 6602, Noise and Fluctuations in Biological, Biophysical, and Biomedical Systems, 66020S (15 June 2007); https://doi.org/10.1117/12.724641

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