TY - GEN
T1 - Can random linear networks store multiple long input streams?
AU - Charles, Adam S.
AU - Yin, Dong
AU - Rozell, Christopher J.
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/2/5
Y1 - 2014/2/5
N2 - The short term memory of randomly connected networks has been recently studied in order to better understand the computational and predictive power of such networks. In particular, random, linear, orthogonal networks have been explored extensively in the context a single input stream driving the network. The most recent results state that a stream of length N can be recovered from a network of size 0(S log6 (N)) assuming that the input is S-sparse in some basis. Little work, however, addresses more complex networks where multiple input streams feed into the same network. In this paper we extend the results for recovering sparse input streams the multiple input streams feeding into the same network. We find that we can recover L input streams of length N with a network that has O (S log5 (LN)) nodes.
AB - The short term memory of randomly connected networks has been recently studied in order to better understand the computational and predictive power of such networks. In particular, random, linear, orthogonal networks have been explored extensively in the context a single input stream driving the network. The most recent results state that a stream of length N can be recovered from a network of size 0(S log6 (N)) assuming that the input is S-sparse in some basis. Little work, however, addresses more complex networks where multiple input streams feed into the same network. In this paper we extend the results for recovering sparse input streams the multiple input streams feeding into the same network. We find that we can recover L input streams of length N with a network that has O (S log5 (LN)) nodes.
KW - Linear neural network
KW - Restricted isometry constant
KW - Short-term memory
KW - Sparse signals
UR - http://www.scopus.com/inward/record.url?scp=84949927396&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84949927396&partnerID=8YFLogxK
U2 - 10.1109/GlobalSIP.2014.7032143
DO - 10.1109/GlobalSIP.2014.7032143
M3 - Conference contribution
AN - SCOPUS:84949927396
T3 - 2014 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2014
SP - 379
EP - 383
BT - 2014 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2014
Y2 - 3 December 2014 through 5 December 2014
ER -