paper-with-me

Papers

Widely Linear Kernels for Complex-Valued Kernel Activation Functions

2019-02-06 · Simone Scardapane, Steven Van Vaerenbergh, Danilo Comminiello, Aurelio Uncini

Complex-valued neural networks (CVNNs) have been shown to be powerful nonlinear approximators when the input data can be properly modeled in the complex domain. One of the major challenges in scaling up CVNNs in practice is the design of complex activation functions. Recently, we proposed a novel framework for learning these activation functions neuron-wise in a data-dependent fashion, based on a cheap one-dimensional kernel expansion and the idea of kernel activation functions (KAFs). In this paper we argue that, despite its flexibility, this framework is still limited in the class of functions that can be modeled in the complex domain. We leverage the idea of widely linear complex kernels to extend the formulation, allowing for a richer expressiveness without an increase in the number of adaptable parameters. We test the resulting model on a set of complex-valued image classification benchmarks. Experimental results show that the resulting CVNNs can achieve higher accuracy while at the same time converging faster.

📄 PDF Abstract BibTeX arXiv:1902.02085

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

The Generalized Complex Kernel Least-Mean-Square Algorithm

2019-02-22 · Rafael Boloix-Tortosa, Juan José Murillo-Fuentes, Sotirios A. Tsaftaris

We propose a novel adaptive kernel based regression method for complex-valued signals: the generalized complex-valued kernel least-mean-square (gCKLMS). We borrow from the new results on widely linear reproducing kernel …

regression

Multiple Operator-valued Kernel Learning

2012-12-01 · NeurIPS 2012 12 · Hachem Kadri, Alain Rakotomamonjy, Philippe Preux, Francis R. Bach

Positive definite operator-valued kernels generalize the well-known notion of reproducing kernels, and are naturally adapted to multi-output learning situations. This paper addresses the problem of learning a finite line…

regression

Random Fourier Features for Operator-Valued Kernels

2016-05-09 · Romain Brault, Florence d'Alché-Buc, Markus Heinonen

Devoted to multi-task learning and structured output learning, operator-valued kernels provide a flexible tool to build vector-valued functions in the context of Reproducing Kernel Hilbert Spaces. To scale up these metho…

Multi-Task LearningTranslation

Complex Diffusion Maps with $ω$-Parameterized Kernels Revealing Inherent Harmonic Representations

2026-05-03 · Tongzhen Dang, Weiyang Ding, Michael K. Ng arxiv

In this paper, we propose Complex Diffusion Maps (CDM), a novel diffusion mapping framework that aims to reveal the dominant complex harmonics of high-dimensional data. Inspired by the local Gaussian kernel relevant to t…

Computational Efficiency

A Unifying View of Explicit and Implicit Feature Maps of Graph Kernels

2017-03-02 · Nils M. Kriege, Marion Neumann, Christopher Morris, Kristian Kersting 외

Non-linear kernel methods can be approximated by fast linear ones using suitable explicit feature maps allowing their application to large scale problems. We investigate how convolution kernels for structured data are co…

Diversity