Integral Equations and Machine Learning
Autor: | Ken Dahm, Alexander Keller |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2017 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning General Computer Science Computer science Monte Carlo method 010103 numerical & computational mathematics 02 engineering and technology Fredholm integral equation 01 natural sciences Theoretical Computer Science Rendering (computer graphics) Machine Learning (cs.LG) symbols.namesake Computer Science - Graphics 0202 electrical engineering electronic engineering information engineering Reinforcement learning 0101 mathematics Numerical Analysis Artificial neural network Applied Mathematics Integral equation Graphics (cs.GR) Image synthesis Modeling and Simulation symbols 020201 artificial intelligence & image processing Approximate solution Algorithm |
Popis: | As both light transport simulation and reinforcement learning are ruled by the same Fredholm integral equation of the second kind, reinforcement learning techniques may be used for photorealistic image synthesis: Efficiency may be dramatically improved by guiding light transport paths by an approximate solution of the integral equation that is learned during rendering. In the light of the recent advances in reinforcement learning for playing games, we investigate the representation of an approximate solution of an integral equation by artificial neural networks and derive a loss function for that purpose. The resulting Monte Carlo and quasi-Monte Carlo methods train neural networks with standard information instead of linear information and naturally are able to generate an arbitrary number of training samples. The methods are demonstrated for applications in light transport simulation. |
Databáze: | OpenAIRE |
Externí odkaz: |