Optimal short-term memory before the edge of chaos in driven random recurrent networks

December 24, 2019 Β· Declared Dead Β· πŸ› Physical Review E

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Taichi Haruna, Kohei Nakajima arXiv ID 1912.11213 Category nlin.AO Cross-listed cond-mat.dis-nn, cs.LG, cs.NE Citations 28 Venue Physical Review E Last Checked 3 months ago
Abstract
The ability of discrete-time nonlinear recurrent neural networks to store time-varying small input signals is investigated by mean-field theory. The combination of a small input strength and mean-field assumptions makes it possible to derive an approximate expression for the conditional probability density of the state of a neuron given a past input signal. From this conditional probability density, we can analytically calculate short-term memory measures, such as memory capacity, mutual information, and Fisher information, and determine the relationships among these measures, which have not been clarified to date to the best of our knowledge. We show that the network contribution of these short-term memory measures peaks before the edge of chaos, where the dynamics of input-driven networks is stable but corresponding systems without input signals are unstable.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” nlin.AO

R.I.P. πŸ‘» Ghosted

When slower is faster

Carlos Gershenson, Dirk Helbing

nlin.AO πŸ› Complex πŸ“š 65 cites 10 years ago

Died the same way β€” πŸ‘» Ghosted