I juni 2017 presenterer Weinan E, Jiequn Han og Arnulf Jentzen en banebrytende algoritme, Deep Backward Stochastic Differential Equation (Deep BSDE), for å løse partielle differensiallikninger (PDEer) ved bruk av dyp læring. I februar 2019 introduserer Côme Huré, Huyên Pham og Xavier Warin en modifikasjon av Deep BSDE, Deep Backward Dynamic Programming (DBDP). DBDP kommer i to varianter. Målet til algoritmene er å unngå dimensjonenes forbannelse. Dette gjøres ved å reformulere PDEene til læringsproblemer. En grundig beskrivelse av det teoretiske fundamentet bak algoritmene er gitt. Vi trenger innsikt i stokastisk analyse for å forstå hvordan PDEer reformuleres til et par stokastiske differensiallikninger. Nevrale nettverk introduseres slik...
In this paper, we propose a network model, the multiclass classification-based reduced order model (...
Backward stochastic differential equations (BSDE) are known to be a powerful tool in mathematical mo...
Pattern recognition has its origins in engineering while machine learning developed from computer sc...
Denne masteroppgaven utforsker en metode for å løse høydimensjonale partielle differentialligninger ...
The objective of this Final Year Project is to study deep learning-based numerical methods, with a f...
In this paper we introduce a numerical method for nonlinear parabolic PDEs that combines operator s...
26 pages, to appear in SIAM Journal of Scientific ComputingRecently proposed numerical algorithms f...
We present a multidimensional deep learning implementation of a stochastic branching algorithm for t...
This work presents a method for the solution of partial diferential equations (PDE’s) using neural n...
Denne masteroppgaven tar for seg hvordan man kan bruke fysikk-informerte nevrale nettverk (FINN) til...
Questa tesi è incentrata sull'analisi di un algoritmo che permette di approssimare una soluzione per...
Solving high-dimensional partial differential equations is a recurrent challenge in economics, scien...
High-dimensional PDEs have been a longstanding computational challenge. We propose to solve high-dim...
Partial differential equations (PDEs) play a central role in the mathematical analysis and modeling ...
In this thesis, we demonstrate the use of machine learning in numerically solving both linear and no...
In this paper, we propose a network model, the multiclass classification-based reduced order model (...
Backward stochastic differential equations (BSDE) are known to be a powerful tool in mathematical mo...
Pattern recognition has its origins in engineering while machine learning developed from computer sc...
Denne masteroppgaven utforsker en metode for å løse høydimensjonale partielle differentialligninger ...
The objective of this Final Year Project is to study deep learning-based numerical methods, with a f...
In this paper we introduce a numerical method for nonlinear parabolic PDEs that combines operator s...
26 pages, to appear in SIAM Journal of Scientific ComputingRecently proposed numerical algorithms f...
We present a multidimensional deep learning implementation of a stochastic branching algorithm for t...
This work presents a method for the solution of partial diferential equations (PDE’s) using neural n...
Denne masteroppgaven tar for seg hvordan man kan bruke fysikk-informerte nevrale nettverk (FINN) til...
Questa tesi è incentrata sull'analisi di un algoritmo che permette di approssimare una soluzione per...
Solving high-dimensional partial differential equations is a recurrent challenge in economics, scien...
High-dimensional PDEs have been a longstanding computational challenge. We propose to solve high-dim...
Partial differential equations (PDEs) play a central role in the mathematical analysis and modeling ...
In this thesis, we demonstrate the use of machine learning in numerically solving both linear and no...
In this paper, we propose a network model, the multiclass classification-based reduced order model (...
Backward stochastic differential equations (BSDE) are known to be a powerful tool in mathematical mo...
Pattern recognition has its origins in engineering while machine learning developed from computer sc...