DeepAI AI Chat
Log In Sign Up

A deep learning based surrogate model for stochastic simulators

by   Akshay Thakur, et al.

We propose a deep learning-based surrogate model for stochastic simulators. The basic idea is to use generative neural network to approximate the stochastic response. The challenge with such a framework resides in designing the network architecture and selecting loss-function suitable for stochastic response. While we utilize a simple feed-forward neural network, we propose to use conditional maximum mean discrepancy (CMMD) as the loss-function. CMMD exploits the property of reproducing kernel Hilbert space and allows capturing discrepancy between the between the target and the neural network predicted distributions. The proposed approach is mathematically rigorous, in the sense that it makes no assumptions about the probability density function of the response. Performance of the proposed approach is illustrated using four benchmark problems selected from the literature. Results obtained indicate the excellent performance of the proposed approach.


page 1

page 2

page 3

page 4


A Method for Estimating Reflectance map and Material using Deep Learning with Synthetic Dataset

The process of decomposing target images into their internal properties ...

A deep learning based reduced order modeling for stochastic underground flow problems

In this paper, we propose a deep learning based reduced order modeling m...

MMD-Bayes: Robust Bayesian Estimation via Maximum Mean Discrepancy

In some misspecified settings, the posterior distribution in Bayesian st...

A General Framework for Machine Learning based Optimization Under Uncertainty

We propose a general framework for machine learning based optimization u...

A Simple Generative Network

Generative neural networks are able to mimic intricate probability distr...

Arithmetic Distribution Neural Network for Background Subtraction

We propose a new Arithmetic Distribution Neural Network (ADNN) for learn...