Neural networks for time-varying data

Richard Rohwer, Fionn Murtagh (Editor)

Research output: Unpublished contribution to conferenceOtherpeer-review

Abstract

This paper reviews some basic issues and methods involved in using neural networks to respond in a desired fashion to a temporally-varying environment. Some popular network models and training methods are introduced. A speech recognition example is then used to illustrate the central difficulty of temporal data processing: learning to notice and remember relevant contextual information. Feedforward network methods are applicable to cases where this problem is not severe. The application of these methods are explained and applications are discussed in the areas of pure mathematics, chemical and physical systems, and economic systems. A more powerful but less practical algorithm for temporal problems, the moving targets algorithm, is sketched and discussed. For completeness, a few remarks are made on reinforcement learning.
Original languageEnglish
Pages59-70
Number of pages12
Publication statusPublished - Dec 1990
EventNeural Networks for Statistical and Economic Data - Dublin, Republic of Ireland
Duration: 10 Dec 199011 Dec 1990

Workshop

WorkshopNeural Networks for Statistical and Economic Data
CityDublin, Republic of Ireland
Period10/12/9011/12/90

Keywords

  • feedforward
  • network
  • algorithm
  • temporal problems
  • moving targets
  • reinforcement learning

Fingerprint

Dive into the research topics of 'Neural networks for time-varying data'. Together they form a unique fingerprint.

Cite this