Autoinverse: Uncertainty Aware Inversion of Neural Networks
This addresses the challenge of deploying neural inverse methods effectively in science and engineering, though it appears incremental as it builds on existing inversion techniques with uncertainty awareness.
The authors tackled the problem of inverting neural network surrogates for real-world applications by proposing Autoinverse, an automated method that leverages predictive uncertainty and reliable training data to find accurate and feasible inverse solutions, achieving high accuracy in control, fabrication, and design tasks.
Neural networks are powerful surrogates for numerous forward processes. The inversion of such surrogates is extremely valuable in science and engineering. The most important property of a successful neural inverse method is the performance of its solutions when deployed in the real world, i.e., on the native forward process (and not only the learned surrogate). We propose Autoinverse, a highly automated approach for inverting neural network surrogates. Our main insight is to seek inverse solutions in the vicinity of reliable data which have been sampled form the forward process and used for training the surrogate model. Autoinverse finds such solutions by taking into account the predictive uncertainty of the surrogate and minimizing it during the inversion. Apart from high accuracy, Autoinverse enforces the feasibility of solutions, comes with embedded regularization, and is initialization free. We verify our proposed method through addressing a set of real-world problems in control, fabrication, and design.