Improved Neural Network Monte Carlo Simulation

09/16/2020
by   I-Kai Chen, et al.
0

The algorithm for Monte Carlo simulation of parton-level events based on an Artificial Neural Network (ANN) proposed in arXiv:1810.11509 is used to perform a simulation of H→ 4ℓ decay. Improvements in the training algorithm have been implemented to avoid numerical instabilities. The integrated decay width evaluated by the ANN is within 0.7 efficiency of 26 between input and output spaces, which can lead to issues with simulation quality, we argue that the training procedure naturally prefers bijective maps, and demonstrate that the trained ANN is bijective to a very good approximation.

READ FULL TEXT
research
11/27/2014

Forecasting the Colorado River Discharge Using an Artificial Neural Network (ANN) Approach

Artificial Neural Network (ANN) based model is a computational approach ...
research
06/04/2020

Neuroevolutionary Transfer Learning of Deep Recurrent Neural Networks through Network-Aware Adaptation

Transfer learning entails taking an artificial neural network (ANN) that...
research
09/08/2010

Artificial Neural Networks, Symmetries and Differential Evolution

Neuroevolution is an active and growing research field, especially in ti...
research
06/26/2019

Adversarial FDI Attack against AC State Estimation with ANN

Artificial neural network (ANN) provides superior accuracy for nonlinear...
research
08/01/2019

A simulation model for longitudinal HIV viral load and mother-to-child-transmission in pregnant and postpartum women

This manuscript describes the model specification, including input and o...
research
10/13/2021

Efficient Estimation in NPIV Models: A Comparison of Various Neural Networks-Based Estimators

We investigate the computational performance of Artificial Neural Networ...
research
10/26/2018

Neural Network-Based Approach to Phase Space Integration

Monte Carlo methods are widely used in particle physics to integrate and...

Please sign up or login with your details

Forgot password? Click here to reset