Succinct Information Processing Unit Seminar (Talk by Dr. Naoya Takeishi, HES-SO, RIKEN-AIP)

Fri, 05 Nov 2021 16:00 - 17:00 JST
Online Link visible to participants

Registration is closed

Get invited to future events

Free admission
-Time Zone:JST -The seats are available on a first-come-first-served basis. -When the seats are fully booked, we may stop accepting applications. -Simultaneous interpretation will not be available.


Naoya Takeishi (HES-SO, RIKEN-AIP)

Learning gray-box deep generative models

Integration of theory-based mathematical models (in physics, chemistry, biology, etc.) and data-driven models has been known as gray-box or hybrid modeling. It 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. In particular, we introduce an architecture of variational autoencoders (VAEs) in which a part of the latent space is grounded by physics. A key technical challenge is to strike a balance between the incomplete physics and trainable components such as neural networks for ensuring that the physics part is used in a meaningful manner. To this end, we propose a regularized learning method that controls the effect of the trainable components and preserves 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.

About this community



Public events of RIKEN Center for Advanced Intelligence Project (AIP)

Join community