ReSuMe - Proof of convergence
نویسنده
چکیده
We consider learning convergence in Spiking Neural Networks trained according to the ReSuMe learning rule. We begin with a short introduction of the ReSuMe learning rules and we define the learning scenarios to be considered. Next, we present a formal proof of learning convergence for the Spike Response Model (SRM) trained according to the defined scenarios. Finally, we demonstrate that the proof made for the SRM holds for the wide class of the spiking neurons. keywords: Spiking Neural Networks, Supervised Learning, Proof of Convergence
منابع مشابه
On the Convergence Analysis of Gravitational Search Algorithm
Gravitational search algorithm (GSA) is one of the newest swarm based optimization algorithms, which has been inspired by the Newtonian laws of gravity and motion. GSA has empirically shown to be an efficient and robust stochastic search algorithm. Since introducing GSA a convergence analysis of this algorithm has not yet been developed. This paper introduces the first attempt to a formal conve...
متن کاملOn the Convergence Analysis of Gravitational Search Algorithm
Gravitational search algorithm (GSA) is one of the newest swarm based optimization algorithms, which has been inspired by the Newtonian laws of gravity and motion. GSA has empirically shown to be an efficient and robust stochastic search algorithm. Since introducing GSA a convergence analysis of this algorithm has not yet been developed. This paper introduces the first attempt to a formal conve...
متن کاملA regularization method for solving a nonlinear backward inverse heat conduction problem using discrete mollification method
The present essay scrutinizes the application of discrete mollification as a filtering procedure to solve a nonlinear backward inverse heat conduction problem in one dimensional space. These problems are seriously ill-posed. So, we combine discrete mollification and space marching method to address the ill-posedness of the proposed problem. Moreover, a proof of stability and<b...
متن کاملOn the Approximation of Pseudo Linear Systems by Linear Time Varying Systems (RESEARCH NOTE)
This paper presents a modified method for approximating nonlinear systems by a sequence of linear time varying systems. The convergence proof is outlined and the potential of this methodology is discussed. Simulation results are used to show the effectiveness of the proposed method.
متن کاملFault tolerant nano-satellite attitude control by adaptive modified nonsingular fast terminal control
In this paper, an adaptive fault tolerant nonlinear control is proposed for attitude tracking problem of satellite with three magnetorquers and one reaction wheel in the presence of inertia uncertainties, external disturbances, and actuator faults. Firstly, sliding surface variable is chosen based on avoiding the singularity of control signal and guaranteeing the convergence of attitude trackin...
متن کامل