New Neural Network Architevture and Algorithm for Memory Sequence Learning and Modelling (CROSBI ID 511007)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Kišasondi, Tonimir ; Lovrenčić, Alen
engleski
New Neural Network Architevture and Algorithm for Memory Sequence Learning and Modelling
In this paper we present a modified neural network architecture and an algorithm that enables neural networks to learn vectors in accordance to user designed sequences. This enables us to use the modified network algorithm to identify, generate or complete specified patterns that are learned in the training phase. The algorithm is based on the idea that neural networks in the human neurocortex represent a distributed memoryof sequences that are stored in invariant hierarchical form with associative access. The algorithm was tested on our custom built simulator that supports the usage of out ADT neural network with standard and our custom built training algorithms.
neural networks; MLP training agorithms; neural network ADT; neural network graph
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
415-422.
2005.
objavljeno
Podaci o matičnoj publikaciji
Conference Proceedings of the 16th International Conference on Information and Intelligent Systems
Aurer, Boris ; Bača, Miroslav
Varaždin: Fakultet organizacije i informatike Sveučilišta u Zagrebu
Podaci o skupu
16th International Conference on Information and Intelligent Systems (16 ; 2005)
predavanje
21.09.2005-23.09.2005
Varaždin, Hrvatska