Memorization of melodies by complex-valued recurrent network

Makoto Kinouchi, Masafumi Hagiwara

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

6 Citations (Scopus)

Abstract

Memorization of the temporal sequences is very important and interesting problem. One of the examples is memorization of melodies. When we memorize melodies, we can recall it from a part. The function can be considered as an associative memory of the temporal sequences. From a technical point of view, it can be considered that the rest of the melody can be determined by some leading some notes. In this paper, we apply the complex-valued recurrent network, which has much superior ability to deal with temporal sequences than the conventional real-valued networks, to memorization of melodies. It is shown in computer simulations that the network can memorize some melodies and recall them correctly from any part.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages1324-1328
Number of pages5
Volume2
Publication statusPublished - 1996
EventProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA
Duration: 1996 Jun 31996 Jun 6

Other

OtherProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
CityWashington, DC, USA
Period96/6/396/6/6

Fingerprint

Data storage equipment
Computer simulation

ASJC Scopus subject areas

  • Software

Cite this

Kinouchi, M., & Hagiwara, M. (1996). Memorization of melodies by complex-valued recurrent network. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 2, pp. 1324-1328). IEEE.

Memorization of melodies by complex-valued recurrent network. / Kinouchi, Makoto; Hagiwara, Masafumi.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 IEEE, 1996. p. 1324-1328.

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

Kinouchi, M & Hagiwara, M 1996, Memorization of melodies by complex-valued recurrent network. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 2, IEEE, pp. 1324-1328, Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, 96/6/3.
Kinouchi M, Hagiwara M. Memorization of melodies by complex-valued recurrent network. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2. IEEE. 1996. p. 1324-1328
Kinouchi, Makoto ; Hagiwara, Masafumi. / Memorization of melodies by complex-valued recurrent network. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 IEEE, 1996. pp. 1324-1328
@inproceedings{abeb1b4be67846e4b2d884b74873fd96,
title = "Memorization of melodies by complex-valued recurrent network",
abstract = "Memorization of the temporal sequences is very important and interesting problem. One of the examples is memorization of melodies. When we memorize melodies, we can recall it from a part. The function can be considered as an associative memory of the temporal sequences. From a technical point of view, it can be considered that the rest of the melody can be determined by some leading some notes. In this paper, we apply the complex-valued recurrent network, which has much superior ability to deal with temporal sequences than the conventional real-valued networks, to memorization of melodies. It is shown in computer simulations that the network can memorize some melodies and recall them correctly from any part.",
author = "Makoto Kinouchi and Masafumi Hagiwara",
year = "1996",
language = "English",
volume = "2",
pages = "1324--1328",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Memorization of melodies by complex-valued recurrent network

AU - Kinouchi, Makoto

AU - Hagiwara, Masafumi

PY - 1996

Y1 - 1996

N2 - Memorization of the temporal sequences is very important and interesting problem. One of the examples is memorization of melodies. When we memorize melodies, we can recall it from a part. The function can be considered as an associative memory of the temporal sequences. From a technical point of view, it can be considered that the rest of the melody can be determined by some leading some notes. In this paper, we apply the complex-valued recurrent network, which has much superior ability to deal with temporal sequences than the conventional real-valued networks, to memorization of melodies. It is shown in computer simulations that the network can memorize some melodies and recall them correctly from any part.

AB - Memorization of the temporal sequences is very important and interesting problem. One of the examples is memorization of melodies. When we memorize melodies, we can recall it from a part. The function can be considered as an associative memory of the temporal sequences. From a technical point of view, it can be considered that the rest of the melody can be determined by some leading some notes. In this paper, we apply the complex-valued recurrent network, which has much superior ability to deal with temporal sequences than the conventional real-valued networks, to memorization of melodies. It is shown in computer simulations that the network can memorize some melodies and recall them correctly from any part.

UR - http://www.scopus.com/inward/record.url?scp=0029767533&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029767533&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029767533

VL - 2

SP - 1324

EP - 1328

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -