2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSPTM-13.3
Paper Title WEIGHT IDENTIFICATION THROUGH GLOBAL OPTIMIZATION IN A NEW HYSTERETIC NEURAL NETWORK MODEL
Authors Elie Leroy, Arthur Marmin, Université Paris-Saclay, CentraleSupélec, Inria, Center for Visual Computing, France; Marc Castella, Samovar, Telecom SudParis, Institut Polytechnique de Paris, France; Laurent Duval, ESIEE Paris, LIGM, Université Gustave-Eiffel and IFP Energies nouvelles, France
SessionSPTM-13: Models, Methods and Algorithms 1
LocationGather.Town
Session Time:Thursday, 10 June, 13:00 - 13:45
Presentation Time:Thursday, 10 June, 13:00 - 13:45
Presentation Poster
Topic Signal Processing Theory and Methods: [SSP] Statistical Signal Processing
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Unlike their biological counterparts, simple artificial neural networks are unable to retain information from their past state to influence their behavior. In this contribution, we propose to consider new nonlinear activation functions, whose outputs depend both from the current and past inputs through a hysteresis effect. This hysteresis model is developed in the framework of convolutional neural networks. We then show that, by choosing the nonlinearity in the vast class of rational functions, the identification of the weights amounts to solving a rational optimization problem. For the latter, recent methods are applicable that come with global optimality guarantee, contrary to most optimization methods used in the neural network community. Finally, simulations show that such hysteresis nonlinear activation functions cannot be approximated by traditional ones and illustrate the effectiveness of our weight identification method.