Pregled bibliografske jedinice broj: 3822
Memory reduction techniques for holographic neurons
Memory reduction techniques for holographic neurons // Proceedings of the 4th international symposium on operations research / Rupnik, Viljem ; Zadnik Stirn, Lidija ; Drobne, Samo ; (ur.).
Preddvor, Slovenija: Slovensko društvo informatika, 1997. str. 195-200 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 3822 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Memory reduction techniques for holographic neurons
Autori
Manger, Robert
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 4th international symposium on operations research
/ Rupnik, Viljem ; Zadnik Stirn, Lidija ; Drobne, Samo ; - : Slovensko društvo informatika, 1997, 195-200
Skup
The 4th International Symposium on Operational Research (SOR"97)
Mjesto i datum
Preddvor, Slovenija, 01.10.1997. - 03.10.1997
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
artificial neural networks; holographic neural technology; memory reduction; forecasting; data compression
Sažetak
This paper shows how certain numerical transformations can be used to control the memory of a holographic neuron. More precisely, the techniques are considered that limit the magnitude or number of entries in the memory matrix, thus reducing the memory persistence and size respectively. Possible applications include short-term forecasting and data compression. Some illustrative experimental results are presented.
Izvorni jezik
Engleski
Znanstvena područja
Matematika
POVEZANOST RADA
Projekti:
037010
Ustanove:
Prirodoslovno-matematički fakultet, Matematički odjel, Zagreb
Profili:
Robert Manger
(autor)
