Repeated sequential learning increases memory capacity via effective decorrelation in a recurrent neural network
June 22, 2019 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Tomoki Kurikawa, Omri Barak, Kunihiko Kaneko
arXiv ID
1906.11770
Category
nlin.AO
Cross-listed
cs.NE,
q-bio.NC
Citations
10
Venue
arXiv.org
Last Checked
3 months ago
Abstract
Memories in neural system are shaped through the interplay of neural and learning dynamics under external inputs. By introducing a simple local learning rule to a neural network, we found that the memory capacity is drastically increased by sequentially repeating the learning steps of input-output mappings. The origin of this enhancement is attributed to the generation of a Psuedo-inverse correlation in the connectivity. This is associated with the emergence of spontaneous activity that intermittently exhibits neural patterns corresponding to embedded memories. Stablization of memories is achieved by a distinct bifurcation from the spontaneous activity under the application of each input.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β nlin.AO
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
When slower is faster
R.I.P.
π»
Ghosted
Performance boost of time-delay reservoir computing by non-resonant clock cycle
R.I.P.
π»
Ghosted
Seeking Open-Ended Evolution in Swarm Chemistry II: Analyzing Long-Term Dynamics via Automated Object Harvesting
R.I.P.
π»
Ghosted
Self-Organization and Artificial Life
R.I.P.
π»
Ghosted
Using Machine Learning to Assess Short Term Causal Dependence and Infer Network Links
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Neural Architecture Search with Reinforcement Learning
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted