Boxlets: A fast convolution algorithm for signal processing and neural networks

Patrice Y. Simard, Léon Bottou, Patrick Haffner, Yann LeCun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Signal processing and pattern recognition algorithms make extensive use of convolution. In many cases, computational accuracy is not as important as computational speed. In feature extraction, for instance, the features of interest in a signal are usually quite distorted. This form of noise justifies some level of quantization in order to achieve faster feature extraction. Our approach consists of approximating regions of the signal with low degree polynomials, and then differentiating the resulting signals in order to obtain impulse functions (or derivatives of impulse functions). With this representation, convolution becomes extremely simple and can be implemented quite effectively. The true convolution can be recovered by integrating the result of the convolution. This method yields substantial speed up in feature extraction and is applicable to convolutional neural networks.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 11 - Proceedings of the 1998 Conference, NIPS 1998
PublisherNeural information processing systems foundation
Pages571-577
Number of pages7
ISBN (Print)0262112450, 9780262112451
StatePublished - 1999
Event12th Annual Conference on Neural Information Processing Systems, NIPS 1998 - Denver, CO, United States
Duration: Nov 30 1998Dec 5 1998

Publication series

NameAdvances in Neural Information Processing Systems
ISSN (Print)1049-5258

Other

Other12th Annual Conference on Neural Information Processing Systems, NIPS 1998
CountryUnited States
CityDenver, CO
Period11/30/9812/5/98

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint Dive into the research topics of 'Boxlets: A fast convolution algorithm for signal processing and neural networks'. Together they form a unique fingerprint.

Cite this