Noise propagation in feedforward and reservoir neural networks

Nadezhda Semenova; Xavier Porte; Maxime Jacquot; Laurent Larger; Daniel Brunner

doi:10.1117/12.2570727

20 August 2020 Noise propagation in feedforward and reservoir neural networks

Nadezhda Semenova, Xavier Porte, Maxime Jacquot, Laurent Larger, Daniel Brunner

Proceedings Volume 11469, Emerging Topics in Artificial Intelligence 2020; 114690J (2020) https://doi.org/10.1117/12.2570727
Event: SPIE Nanoscience + Engineering, 2020, Online Only

Abstract

Maximal computing performance can only be achieved if neural networks are fully hardware implemented. Besides the potentially large benefits, such parallel and analogue hardware platforms face new, fundamental challenges. An important concern is that such systems might ultimately succumb to the detrimental impact of noise. We study of noise propagation through deep neural networks with various neuron nonlinearities and trained via back-propagation for image recognition and time-series prediction. We consider correlated and uncorrelated, multiplicative and additive noise and use noise amplitudes extracted from a physical experiment. The developed analytical framework is of great relevance for future hardware neural networks. It allows predicting the noise level at the system’s output based on the properties of its constituents. As such it is an essential tool for future hardware neural network engineering and performance estimation.

Conference Presentation

Citation Download Citation

Nadezhda Semenova, Xavier Porte, Maxime Jacquot, Laurent Larger, and Daniel Brunner "Noise propagation in feedforward and reservoir neural networks", Proc. SPIE 11469, Emerging Topics in Artificial Intelligence 2020, 114690J (20 August 2020); https://doi.org/10.1117/12.2570727

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
PRESENTATION

WATCH
PRESENTATION SAVE TO MY LIBRARY

GET CITATION

KEYWORDS

Neural networks

Neurons

Chaos

Numerical simulations

RELATED CONTENT

Realisation of large-scale photonic spiking hardware system
Proceedings of SPIE (October 03 2022)

Rotation, scale, and translation invariant pattern recognition using feature extraction
Proceedings of SPIE (March 27 1997)

Precision of a radial basis function neural network tracking method
Proceedings of SPIE (August 06 2003)

Application of modified Kohnen's network to optimization problems
Proceedings of SPIE (March 05 2007)

Use of Feynman diagrams in large scale neural networks with...
Proceedings of SPIE (November 05 1993)

Memory capacity of terminal attractor optical associative memory
Proceedings of SPIE (September 20 1996)

Geometry of phase space and asymptotic behavior for oscillatory neural...
Proceedings of SPIE (March 25 1998)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years