A class of neural networks based on approximate identity for analog IC's hardware implementation

• CONTI M.

  Dipartimento di Elettronica e Automatica, Universita di Ancona

• Orcioni Simone

  Dipartimento di Elettronica e Automatica, Universita di Ancona

• Turchetti Claudio

  Dipartimento di Elettronica e Automatica, Universita di Ancona

抄録

Artificial Neural Networks (ANN's) that are able to learn exhibit many interesting features making them suitable to be applied in several fields such as pattern recognition, computer vision and so forth. Learning a given input-output mapping can be regarded as a problem of approximating a multivariate function. In this paper we will report a theoretical framework for approximation, based on the well known sequences of functions named approximate identities. In particular, it is proven that such sequences are able to approximate a generally continuous function to any degree of accuracy. On the basis of these theoretical results, it is shown that the proposed approximation scheme maps into a class of networks which can efficiently be implemented with analog MOS VLSI or BJT integrated circuits. To prove the validity of the proposed approach a series of results is reported.

収録刊行物

• IEICE Trans. Fundamentals of Electronics, Communications and Computer Science, Japan

  IEICE Trans. Fundamentals of Electronics, Communications and Computer Science, Japan 77 (6), 1069-1079, 1994

  一般社団法人電子情報通信学会

詳細情報

• CRID: 1571698602418416256
• NII論文ID: 110003215844
• NII書誌ID: AA10826239
• ISSN: 09168508
• 本文言語コード: en
• データソース種別:
  • CiNii Articles