Recursive Multikernel Filters Exploiting Nonlinear Temporal Structure release_uklhpkyvrbacta6ca3nptvkn7q

by Steven Van Vaerenbergh, Simone Scardapane, Ignacio Santamaria

Released as a article .

2017  

Abstract

In kernel methods, temporal information on the data is commonly included by using time-delayed embeddings as inputs. Recently, an alternative formulation was proposed by defining a gamma-filter explicitly in a reproducing kernel Hilbert space, giving rise to a complex model where multiple kernels operate on different temporal combinations of the input signal. In the original formulation, the kernels are then simply combined to obtain a single kernel matrix (for instance by averaging), which provides computational benefits but discards important information on the temporal structure of the signal. Inspired by works on multiple kernel learning, we overcome this drawback by considering the different kernels separately. We propose an efficient strategy to adaptively combine and select these kernels during the training phase. The resulting batch and online algorithms automatically learn to process highly nonlinear temporal information extracted from the input signal, which is implicitly encoded in the kernel values. We evaluate our proposal on several artificial and real tasks, showing that it can outperform classical approaches both in batch and online settings.
In text/plain format

Archived Files and Locations

application/pdf  356.9 kB
file_l2tddb6y6zdxrp25l3xhlinq5m
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2017-06-12
Version   v1
Language   en ?
arXiv  1706.03533v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 86af8099-1419-4873-b656-446327fbdf74
API URL: JSON