DeepAI AI Chat
Log In Sign Up

Synchronization and Redundancy: Implications for Robustness of Neural Learning and Decision Making

by   Jake Bouvrie, et al.
Duke University

Learning and decision making in the brain are key processes critical to survival, and yet are processes implemented by non-ideal biological building blocks which can impose significant error. We explore quantitatively how the brain might cope with this inherent source of error by taking advantage of two ubiquitous mechanisms, redundancy and synchronization. In particular we consider a neural process whose goal is to learn a decision function by implementing a nonlinear gradient dynamics. The dynamics, however, are assumed to be corrupted by perturbations modeling the error which might be incurred due to limitations of the biology, intrinsic neuronal noise, and imperfect measurements. We show that error, and the associated uncertainty surrounding a learned solution, can be controlled in large part by trading off synchronization strength among multiple redundant neural systems against the noise amplitude. The impact of the coupling between such redundant systems is quantified by the spectrum of the network Laplacian, and we discuss the role of network topology in synchronization and in reducing the effect of noise. A range of situations in which the mechanisms we model arise in brain science are discussed, and we draw attention to experimental evidence suggesting that cortical circuits capable of implementing the computations of interest here can be found on several scales. Finally, simulations comparing theoretical bounds to the relevant empirical quantities show that the theoretical estimates we derive can be tight.


page 4

page 5

page 6

page 7

page 9

page 10

page 12

page 13


A continuous-time analysis of distributed stochastic gradient

Synchronization in distributed networks of nonlinear dynamical systems p...

Model reconstruction from temporal data for coupled oscillator networks

In a complex system, the interactions between individual agents often le...

Switching dynamics of single and coupled VO2-based oscillators as elements of neural networks

In the present paper, we report on the switching dynamics of both single...

Dependable Neural Networks Through Redundancy, A Comparison of Redundant Architectures

With edge-AI finding an increasing number of real-world applications, es...

Prescribed-Time Synchronization of Multiweighted and Directed Complex Networks

In this note, we study the prescribed-time (PT) synchronization of multi...

Conflict-free joint decision by lag and zero-lag synchronization in laser network

With the end of Moore's Law and the increasing demand for computing, pho...

Noise-induced synchronization of self-organized systems: Hegselmann-Krause dynamics in infinite space

It has been well established the theoretical analysis for the noise-indu...