Resilience Pattern in Neural Network, M.Sc. Thesis Sharif University of Technology ; Rahimi Tabar, Mohammad Reza (Supervisor)
Abstract
In this thesis the resilience of a neural network is examined under structural perturbation.The network consists of Spiking neurons with specific dynamics or they are binary neurons and the network is non-spiking. Neural network is a multi-dimensional and multi-stable system therefore we can map their dynamical equations to effective one-dimensional equation with one parameter which shows the environmental conditions.The resilience of the system is evaluated with respect to changes in weights and edges of the network and the the resilience pattern of the system is obtained.Finally, the recovery and control methods are briefly discussed
Cataloging briefResilience Pattern in Neural Network, M.Sc. Thesis Sharif University of Technology ; Rahimi Tabar, Mohammad Reza (Supervisor)
Abstract
In this thesis the resilience of a neural network is examined under structural perturbation.The network consists of Spiking neurons with specific dynamics or they are binary neurons and the network is non-spiking. Neural network is a multi-dimensional and multi-stable system therefore we can map their dynamical equations to effective one-dimensional equation with one parameter which shows the environmental conditions.The resilience of the system is evaluated with respect to changes in weights and edges of the network and the the resilience pattern of the system is obtained.Finally, the recovery and control methods are briefly discussed
Find in contentBookmark
|
|