Designing a digital neurocomputer - Improving ANN processing with a dedicated hardware system

P. Kolinummi; Timo Hämäläinen; K. Kaski

doi:10.1109/101.583608

Designing a digital neurocomputer - Improving ANN processing with a dedicated hardware system

P. Kolinummi, Timo Hämäläinen, K. Kaski

Not published at Aalto University

Research output: Contribution to journal › Article › Scientific › peer-review

2 Citations (Scopus)

Abstract

In this article we discuss the flow of design for neural network hardware and go deeper into the design constraints and implementation possibilities. The performance measures and problems of different measurements are also discussed. It is noted that performance is one comparison criteria, but there are also many others, some of which are also discussed. In order to anchor the discussion to real life, the article includes a case study of our TUTNC neurocomputer. In addition, examples of commercial neural computing systems and their world wide web pages are given.

Original language	English
Pages (from-to)	19-27
Journal	IEEE Circuits and Devices Magazine
Volume	13
Issue number	2
DOIs	https://doi.org/10.1109/101.583608
Publication status	Published - 1997
MoE publication type	A1 Journal article-refereed

Access to Document

10.1109/101.583608

Cite this

@article{f50736cbb0304cc6940e3f2de6d18a15,

title = "Designing a digital neurocomputer - Improving ANN processing with a dedicated hardware system",

abstract = "In this article we discuss the flow of design for neural network hardware and go deeper into the design constraints and implementation possibilities. The performance measures and problems of different measurements are also discussed. It is noted that performance is one comparison criteria, but there are also many others, some of which are also discussed. In order to anchor the discussion to real life, the article includes a case study of our TUTNC neurocomputer. In addition, examples of commercial neural computing systems and their world wide web pages are given.",

keywords = "improving ANN processinge, improving ANN processinge",

author = "P. Kolinummi and Timo H{\"a}m{\"a}l{\"a}inen and K. Kaski",

year = "1997",

doi = "10.1109/101.583608",

language = "English",

volume = "13",

pages = "19--27",

journal = "IEEE Circuits and Devices Magazine",

issn = "8755-3996",

publisher = "IEEE",

number = "2",

}

TY - JOUR

T1 - Designing a digital neurocomputer - Improving ANN processing with a dedicated hardware system

AU - Kolinummi, P.

AU - Hämäläinen, Timo

AU - Kaski, K.

PY - 1997

Y1 - 1997

N2 - In this article we discuss the flow of design for neural network hardware and go deeper into the design constraints and implementation possibilities. The performance measures and problems of different measurements are also discussed. It is noted that performance is one comparison criteria, but there are also many others, some of which are also discussed. In order to anchor the discussion to real life, the article includes a case study of our TUTNC neurocomputer. In addition, examples of commercial neural computing systems and their world wide web pages are given.

AB - In this article we discuss the flow of design for neural network hardware and go deeper into the design constraints and implementation possibilities. The performance measures and problems of different measurements are also discussed. It is noted that performance is one comparison criteria, but there are also many others, some of which are also discussed. In order to anchor the discussion to real life, the article includes a case study of our TUTNC neurocomputer. In addition, examples of commercial neural computing systems and their world wide web pages are given.

KW - improving ANN processinge

U2 - 10.1109/101.583608

DO - 10.1109/101.583608

M3 - Article

SN - 8755-3996

VL - 13

SP - 19

EP - 27

JO - IEEE Circuits and Devices Magazine

JF - IEEE Circuits and Devices Magazine

IS - 2

ER -

Designing a digital neurocomputer - Improving ANN processing with a dedicated hardware system

Abstract

Access to Document

Fingerprint

Cite this