Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling

02/25/2021
by   Naoya Takeishi, et al.
10

Integrating physics models within machine learning holds considerable promise toward learning robust models with improved interpretability and abilities to extrapolate. In this work, we focus on the integration of incomplete physics models into deep generative models, variational autoencoders (VAEs) in particular. A key technical challenge is to strike a balance between the incomplete physics model and the learned components (i.e., neural nets) of the complete model, in order to ensure that the physics part is used in a meaningful manner. To this end, we propose a VAE architecture in which a part of the latent space is grounded by physics. We couple it with a set of regularizers that control the effect of the learned components and preserve the semantics of the physics-based latent variables as intended. We not only demonstrate generative performance improvements over a set of synthetic and real-world datasets, but we also show that we learn robust models that can consistently extrapolate beyond the training distribution in a meaningful manner. Moreover, we show that we can control the generative process in an interpretable manner.

READ FULL TEXT

page 7

page 8

page 15

page 16

research
07/18/2023

Interpretable Timbre Synthesis using Variational Autoencoders Regularized on Timbre Descriptors

Controllable timbre synthesis has been a subject of research for several...
research
01/24/2019

On the Transformation of Latent Space in Autoencoders

Noting the importance of the latent variables in inference and learning,...
research
11/21/2018

Physics-aware Deep Generative Models for Creating Synthetic Microstructures

A key problem in computational material science deals with understanding...
research
07/16/2021

Machine-learning Kondo physics using variational autoencoders

We employ variational autoencoders to extract physical insight from a da...
research
04/13/2022

Hybrid Neural Network Augmented Physics-based Models for Nonlinear Filtering

In this paper we present a hybrid neural network augmented physics-based...
research
10/12/2019

Disentangling Interpretable Generative Parameters of Random and Real-World Graphs

While a wide range of interpretable generative procedures for graphs exi...
research
08/29/2018

Interpretable Intuitive Physics Model

Humans have a remarkable ability to use physical commonsense and predict...

Please sign up or login with your details

Forgot password? Click here to reset