Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
2000-07-05
Physical Review E 62(2) (2000)
Physics
Condensed Matter
Disordered Systems and Neural Networks
5 pages, 3 figures, accepted for publication in Physical Review E
Scientific paper
10.1103/PhysRevE.62.1617
We study the capability to learn and to generate long-range, power-law correlated sequences by a fully connected asymmetric network. The focus is set on the ability of neural networks to extract statistical features from a sequence. We demonstrate that the average power-law behavior is learnable, namely, the sequence generated by the trained network obeys the same statistical behavior. The interplay between a correlated weight matrix and the sequence generated by such a network is explored. A weight matrix with a power-law correlation function along the vertical direction, gives rise to a sequence with a similar statistical behavior.
Kanter Ido
Priel Avner
No associations
LandOfFree
Learning and generation of long-range correlated sequences does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Learning and generation of long-range correlated sequences, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning and generation of long-range correlated sequences will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-171517