Learning Inverse Mappings with Deep Neural Networks

Dnr:

NAISS 2023/5-78

Type:

NAISS Medium Compute

Principal Investigator:

Prashant Singh

Affiliation:

Uppsala universitet

Start Date:

2023-02-23

End Date:

2024-03-01

Primary Classification:

10201: Computer Sciences

Secondary Classification:

10203: Bioinformatics (Computational Biology) (applications to be 10610)

Webpage:

Several inverse and optimization problems involve the use of simulation models. Examples of such problems include simulation-based optimization, simulation-based (parameter) inference, identifying quasi-optimal regions in computer-aided design, etc. The simulation models represent complex real-world phenomena and therefore are often computationally expensive to evaluate. Consequently, it is desirable to minimise the number of simulations involved in solving the inverse and optimization problems. We explore neural networks as surrogate models that learn the inverse mapping between simulator response as neural network input, and simulator parameters as neural network outputs. This project will investigate convolutional networks and variational autoencoders to learn the inverse mappings.