Expressive Power of Non-deterministic Evolving Recurrent Neural Networks in Terms of Their Attractor Dynamics

2015 ◽  
pp. 144-156 ◽  
Author(s):  
Jérémie Cabessa ◽  
Jacques Duparc
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Expressive Power ◽  
Attractor Dynamics

scholarly journals The expressive power of analog recurrent neural networks on infinite input streams

2012 ◽  
Vol 436 ◽  
pp. 23-34 ◽  
Author(s):  
Jérémie Cabessa ◽  
Alessandro E.P. Villa
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Expressive Power

Nonlinear enhancement of noisy speech, using continuous attractor dynamics formed in recurrent neural networks

2011 ◽  
Vol 74 (17) ◽  
pp. 2716-2724 ◽  
Author(s):  
Louiza Dehyadegary ◽  
Seyyed Ali Seyyedsalehi ◽  
Isar Nejadgholi
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Noisy Speech ◽  
Attractor Dynamics

scholarly journals Robust Working Memory through Short-Term Synaptic Plasticity

2022 ◽  
Author(s):  
Leo Kozachkov ◽  
John Tauber ◽  
Mikael Lundqvist ◽  
Scott L Brincat ◽  
Jean-Jacques Slotine ◽  
...  
Keyword(s):  
Neural Networks ◽  
Working Memory ◽  
Synaptic Plasticity ◽  
Recent Work ◽  
Recurrent Neural Networks ◽  
Memory Task ◽  
Short Term ◽  
Attractor Dynamics ◽  
Robust To Noise

Working memory has long been thought to arise from sustained spiking/attractor dynamics. However, recent work has suggested that short-term synaptic plasticity (STSP) may help maintain attractor states over gaps in time with little or no spiking. To determine if STSP endows additional functional advantages, we trained artificial recurrent neural networks (RNNs) with and without STSP to perform an object working memory task. We found that RNNs with and without STSP were both able to maintain memories over distractors presented in the middle of the memory delay. However, RNNs with STSP showed activity that was similar to that seen in the cortex of monkeys performing the same task. By contrast, RNNs without STSP showed activity that was less brain-like. Further, RNNs with STSP were more robust to noise and network degradation than RNNs without STSP. These results show that STSP can not only help maintain working memories, it also makes neural networks more robust.

Sign in / Sign up

Export Citation Format

Share Document