Stability Analysis of Recurrent Shunting On-Center Off-Surround Neural Networks with Nonlinear Transfer Functions
Rakesh Sengupta, Usha Desai · 2025
Understanding the stability and dynamics of neural networks is crucial for advancing our knowledge of cognitive processes and developing effective neural models. Shunting recurrent networks, with their complex interactions and non-linear dynamics, offer a useful framework for exploring fundamental aspects of neural behavior. This work is motivated by the need to comprehensively assess stability conditions and dynamic responses of such networks to transient inputs, as well as to bridge the gap between theoretical stability analysis and practical network behavior. By examining both simultaneous and sequential input presentations, we aim to shed light on the network’s capacity to model memory processes and validate stability criteria through empirical simulations and theoretical analysis.