Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Zhan, Eric"'
Autor:
Neckrasov, Vasiliy, Zhan, Eric
In this paper we completely describe the winning and losing conditions different from the only ``trivial'' conditions known before. In other words, we solve the open question of finding a complete nontrivial Schmidt diagram. In addition, we give the
Externí odkaz:
http://arxiv.org/abs/2401.00614
Autor:
Zhan, Eric
Raw behavioral data is becoming increasingly more abundant and more easily obtainable in spatiotemporal domains such as sports, video games, navigation & driving, motion capture, and animal science. How can we best use this data to advance their resp
We present a framework for the unsupervised learning of neurosymbolic encoders, which are encoders obtained by composing neural networks with symbolic programs from a domain-specific language. Our framework naturally incorporates symbolic expert know
Externí odkaz:
http://arxiv.org/abs/2107.13132
Autor:
Stephenson, Oliver L., Köhne, Tobias, Zhan, Eric, Cahill, Brent E., Yun, Sang-Ho, Ross, Zachary E., Simons, Mark
Publikováno v:
IEEE Transactions on Geoscience and Remote Sensing (2021)
Satellite remote sensing is playing an increasing role in the rapid mapping of damage after natural disasters. In particular, synthetic aperture radar (SAR) can image the Earth's surface and map damage in all weather conditions, day and night. Howeve
Externí odkaz:
http://arxiv.org/abs/2105.11544
Specialized domain knowledge is often necessary to accurately annotate training sets for in-depth analysis, but can be burdensome and time-consuming to acquire from domain experts. This issue arises prominently in automated behavior analysis, in whic
Externí odkaz:
http://arxiv.org/abs/2011.13917
We study the problem of learning differentiable functions expressed as programs in a domain-specific language. Such programmatic models can offer benefits such as composability and interpretability; however, learning them requires optimizing over a c
Externí odkaz:
http://arxiv.org/abs/2007.12101
We study the problem of controllable generation of long-term sequential behaviors, where the goal is to calibrate to multiple behavior styles simultaneously. In contrast to the well-studied areas of controllable generation of images, text, and speech
Externí odkaz:
http://arxiv.org/abs/1910.01179
Missing value imputation is a fundamental problem in spatiotemporal modeling, from motion tracking to the dynamics of physical systems. Deep autoregressive models suffer from error propagation which becomes catastrophic for imputing long-range sequen
Externí odkaz:
http://arxiv.org/abs/1901.10946
We study the problem of training sequential generative models for capturing coordinated multi-agent trajectory behavior, such as offensive basketball gameplay. When modeling such settings, it is often beneficial to design hierarchical models that can
Externí odkaz:
http://arxiv.org/abs/1803.07612
Publikováno v:
In Measurement 30 November 2022 204