By Hamid Krim
Machine Learning (ML) has reached an unprecedented performance in various inference problems arising in practice. The sample complexity and that of the model have, however, increasingly emerged as a serious limitation. Given the importance of a number of problems where these issues are central, we have revisited the Conv-net fundamental principle and have reformulated it from a Volterra Series perspective using a polynomial functional paradigm*. We propose a computational Convolutional Network solution which requires no activation function and provides a very competitive inference performance (often better) at a fraction of the sample and model complexity of the most competitive CNN architecture. * Homogeneous Polynomial Functional were first developed and formalized by Frechet
By Eero Simoncelli
By Naoki Saito
By Maarten de Hoop
By Martin Vetterli
By Maureen Clerc
By Irène Waldspurger
By Jérôme Kalifa
By Gitta Kutyniok
By Michael Unser
By Edouard Oyallon
By Remi Gribonval
By Giuseppe Savaré
By Ronnie Pavlov
By Ronnie Pavlov
By Tamara Kucherenko
