English
Related papers

Related papers: Phase Harmonic Correlations and Convolutional Neur…

200 papers

We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as vectors in a…

Machine Learning · Computer Science 2016-09-06 Yuchen Zhang , Percy Liang , Martin J. Wainwright

This paper addresses the analysis and design of non-reciprocal filters based on time modulated resonators. We analytically show that time modulating a resonator leads to a set of harmonic resonators composed of the unmodulated lumped…

Signal Processing · Electrical Eng. & Systems 2020-02-19 A. Alvarez-Melcon , X. Wu , J. Zang , X. Liu , J. S. Gomez-Diaz

Selecting appropriate inductive biases is an essential step in the design of machine learning models, especially when working with audio, where even short clips may contain millions of samples. To this end, we propose the combolutional…

Sound · Computer Science 2025-08-06 Cameron Churchwell , Minje Kim , Paris Smaragdis

We present an approach which enables to state about the existence of phase synchronization in coupled chaotic oscillators without having to measure the phase. This is done by observing the oscillators at special times, and analyzing whether…

Statistical Mechanics · Physics 2009-11-13 T. Pereira , M. S. Baptista , J. Kurths

Many voice disorders induce subharmonic phonation, but voice signal analysis is currently lacking a technique to detect the presence of subharmonics reliably. Distinguishing subharmonic phonation from normal phonation is a challenging task…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-17 Takeshi Ikuma , Melda Kunduk , Brad Story , Andrew J. McWhorter

Network coherence generally refers to the emergence of simple aggregated dynamical behaviours, despite heterogeneity in the dynamics of the subsystems that constitute the network. In this paper, we develop a general frequency domain…

Systems and Control · Electrical Eng. & Systems 2023-02-17 Hancheng Min , Richard Pates , Enrique Mallada

We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN). We first notice CNN's ability in capturing the high-frequency components of images. These…

Computer Vision and Pattern Recognition · Computer Science 2020-03-26 Haohan Wang , Xindi Wu , Zeyi Huang , Eric P. Xing

We apply persistent homology to the task of discovering and characterizing phase transitions, using lattice spin models from statistical physics for working examples. Persistence images provide a useful representation of the homological…

Statistical Mechanics · Physics 2020-12-03 Alex Cole , Gregory J. Loges , Gary Shiu

Understanding complex systems which exhibit desynchronization as an emergent property should have important implications, particularly in treating neurological disorders and designing efficient communication networks. Here were demonstrate…

Mathematical Physics · Physics 2012-11-06 J. Borresen , D. Broomhead

Nonlinear relations among frequencies and phases in modulational instability of circularly polarized Alfven waves are discussed, within the context of one dimensional, dissipation-less, unforced fluid system. We show that generation of…

Plasma Physics · Physics 2020-01-29 Yasuhiro Nariyuki , Tohru Hada

Convolutional Neural Networks (CNNs) are a class of artificial neural networks whose computational blocks use convolution, together with other linear and non-linear operations, to perform classification or regression. This paper explores…

Computer Vision and Pattern Recognition · Computer Science 2018-10-09 Victor Stamatescu , Mark D. McDonnell

Applications of neural networks to condensed matter physics are becoming popular and beginning to be well accepted. Obtaining and representing the ground and excited state wave functions are examples of such applications. Another…

Disordered Systems and Neural Networks · Physics 2019-12-30 Tomi Ohtsuki , Tomohiro Mano

The phase oscillator model with global coupling is extended to the case of finite-range nonlocal coupling. Under suitable conditions, peculiar patterns emerge in which a quasi-continuous array of identical oscillators separates sharply into…

Statistical Mechanics · Physics 2007-05-23 Yoshiki Kuramoto , Dorjsuren Battogtokh

Networks of coupled phase oscillators are one of the most studied dynamical systems with numerous applications in physics, chemistry, biology, and engineering. Their behaviour is often characterized by the emergence of various partially…

Pattern Formation and Solitons · Physics 2026-02-27 Oleh E. Omel'chenko

The windowed quadratic phase Fourier transform (WQPFT) combines the localization capabilities of windowed transforms with the phase modulation structure of the quadratic phase Fourier transform (QPFT). This paper investigates fundamental…

Functional Analysis · Mathematics 2025-07-09 Sarga Varghese , Manab Kundu

Convolutional networks are large linear systems divided into layers and connected by non-linear units. These units are the "articulations" that allow the network to adapt to the input. To understand how a network manages to solve a problem…

Computer Vision and Pattern Recognition · Computer Science 2019-11-15 Pablo Navarrete Michelini , Hanwen Liu , Yunhua Lu , Xingqun Jiang

Many phenomena are described by bivariate signals or bidimensional vectors in applications ranging from radar to EEG, optics and oceanography. The time-frequency analysis of bivariate signals is usually carried out by analyzing two separate…

Methodology · Statistics 2016-09-09 Julien Flamant , Nicolas Le Bihan , Pierre Chainais

Rhythmic activities that alternate between coherent and incoherent phases are ubiquitous in chemical, ecological, climate, or neural systems. Despite their importance, general mechanisms for their emergence are little understood. In order…

Adaptation and Self-Organizing Systems · Physics 2022-06-01 Max Thiele , Rico Berner , Peter A. Tass , Eckehard Schöll , Serhiy Yanchuk

Coherent diffractive imaging is a technique that recovers the sample image by numerically inverting its diffraction pattern. We propose a generalization of this method for the inversion of multi-wavelength data. Using this approach, we show…

Optics · Physics 2020-05-08 Erik Malm , Edwin Fohtung , Anders Mikkelsen

Deep convolutional classifiers linearly separate image classes and improve accuracy as depth increases. They progressively reduce the spatial dimension whereas the number of channels grows with depth. Spatial variability is therefore…

Machine Learning · Computer Science 2022-03-22 Florentin Guth , John Zarka , Stéphane Mallat