Benchmarking deep inverse models over time, and the neural-adjoint method

09/27/2020
by   Simiao Ren, et al.
0

We consider the task of solving generic inverse problems, where one wishes to determine the hidden parameters of a natural system that will give rise to a particular set of measurements. Recently many new approaches based upon deep learning have arisen generating impressive results. We conceptualize these models as different schemes for efficiently, but randomly, exploring the space of possible inverse solutions. As a result, the accuracy of each approach should be evaluated as a function of time rather than a single estimated solution, as is often done now. Using this metric, we compare several state-of-the-art inverse modeling approaches on four benchmark tasks: two existing tasks, one simple task for visualization and one new task from metamaterial design. Finally, inspired by our conception of the inverse problem, we explore a solution that uses a deep learning model to approximate the forward model, and then uses backpropagation to search for good inverse solutions. This approach, termed the neural-adjoint, achieves the best performance in many scenarios.

READ FULL TEXT
research
11/25/2022

Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modeling

We propose and show the efficacy of a new method to address generic inve...
research
12/02/2022

Accelerating Inverse Learning via Intelligent Localization with Exploratory Sampling

In the scope of "AI for Science", solving inverse problems is a longstan...
research
06/28/2018

Deep learning for dehazing: Comparison and analysis

We compare a recent dehazing method based on deep learning, Dehazenet, w...
research
12/19/2021

Inverse deep learning methods and benchmarks for artificial electromagnetic material design

Deep learning (DL) inverse techniques have increased the speed of artifi...
research
12/03/2018

Deep Inverse Optimization

Given a set of observations generated by an optimization process, the go...
research
04/20/2020

Deep Learning for One-dimensional Consolidation

Neural networks with physical governing equations as constraints have re...
research
02/27/2022

Deep Learning-Based Inverse Design for Engineering Systems: Multidisciplinary Design Optimization of Automotive Brakes

The braking performance of the brake system is a target performance that...

Please sign up or login with your details

Forgot password? Click here to reset