Abstract
Inhibitory neural networks are found to encode high volumes of information through delayed inhibition. We show that inhibition delay increases storage capacity through a Stirling transform of the minimum capacity which stabilizes locally coherent oscillations. We obtain both the exact and asymptotic formulas for the total number of dynamic attractors. Our results predict a (ln2)-N-fold increase in capacity for an N-neuron network and demonstrate high-density associative memories which host a maximum number of oscillations in analog neural devices.
Original language | English |
---|---|
Article number | 030301(R) |
Pages (from-to) | 1-4 |
Number of pages | 4 |
Journal | Physical Review E |
Volume | 97 |
Issue number | 3 |
Early online date | 9 Mar 2018 |
DOIs | |
Publication status | Published - 9 Mar 2018 |
Fingerprint
ASJC Scopus subject areas
- Statistical and Nonlinear Physics
- Statistics and Probability
- Condensed Matter Physics
Cite this
Inhibition Delay Increases Neural Network Capacity through Stirling Transform. / Nogaret, Alain; King, Alastair.
In: Physical Review E, Vol. 97, No. 3, 030301(R), 09.03.2018, p. 1-4.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Inhibition Delay Increases Neural Network Capacity through Stirling Transform
AU - Nogaret, Alain
AU - King, Alastair
PY - 2018/3/9
Y1 - 2018/3/9
N2 - Inhibitory neural networks are found to encode high volumes of information through delayed inhibition. We show that inhibition delay increases storage capacity through a Stirling transform of the minimum capacity which stabilizes locally coherent oscillations. We obtain both the exact and asymptotic formulas for the total number of dynamic attractors. Our results predict a (ln2)-N-fold increase in capacity for an N-neuron network and demonstrate high-density associative memories which host a maximum number of oscillations in analog neural devices.
AB - Inhibitory neural networks are found to encode high volumes of information through delayed inhibition. We show that inhibition delay increases storage capacity through a Stirling transform of the minimum capacity which stabilizes locally coherent oscillations. We obtain both the exact and asymptotic formulas for the total number of dynamic attractors. Our results predict a (ln2)-N-fold increase in capacity for an N-neuron network and demonstrate high-density associative memories which host a maximum number of oscillations in analog neural devices.
UR - http://www.scopus.com/inward/record.url?scp=85044216171&partnerID=8YFLogxK
U2 - 10.1103/PhysRevE.97.030301
DO - 10.1103/PhysRevE.97.030301
M3 - Article
VL - 97
SP - 1
EP - 4
JO - Physical Review E
JF - Physical Review E
SN - 1539-3755
IS - 3
M1 - 030301(R)
ER -