Home /

Research

Showing 325 - 330 / 897

Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model


Authors:  JuntaoLi, RuidanHe, HaiYe....
Published date-11/23/2020
Tasks:  DomainAdaptation, LanguageModelling, MutualInformationEstimation, UnsupervisedDomainAdaptation

Abstract: Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements over various cross-lingual and low-resource tasks. Through training on one hundred languages and terabytes …

Discovering Causal Structure with Reproducing-Kernel Hilbert Space $ε$-Machines


Authors:  NicolasBrodu, JamesP.Crutchfield....
Published date-11/23/2020

Abstract: We merge computational mechanics' definition of causal states (predictively-equivalent histories) with reproducing-kernel Hilbert space (RKHS) representation inference. The result is a widely-applicable method that infers causal structure directly from observations …

Evolutionary Planning in Latent Space


Authors:  ThorV.A.N.Olesen, DennisT.T.Nguyen, RasmusBergPalm....
Published date-11/23/2020

Abstract: Planning is a powerful approach to reinforcement learning with several desirable properties. However, it requires a model of the world, which is not readily available in many real-life problems. In …

End-to-End Framework for Efficient Deep Learning Using Metasurfaces Optics


Authors:  CarlosMauricioVillegasBurgos, TianqiYang, NickVamivakas....
Published date-11/23/2020

Abstract: Deep learning using Convolutional Neural Networks (CNNs) has been shown to significantly out-performed many conventional vision algorithms. Despite efforts to increase the CNN efficiency both algorithmically and with specialized hardware, …

Cycle-consistent Generative Adversarial Networks for Neural Style Transfer using data from Chang'E-4


Authors:  J.deCurtó, R.Duvall....
Published date-11/23/2020
Tasks:  StyleTransfer

Abstract: Generative Adversarial Networks (GANs) have had tremendous applications in Computer Vision. Yet, in the context of space science and planetary exploration the door is open for major advances. We introduce …

Planar 3D Transfer Learning for End to End Unimodal MRI Unbalanced Data Segmentation


Authors:  MartinKolarik, RadimBurget, CarlosM.Travieso-Gonzalez....
Published date-11/23/2020
Tasks:  LesionSegmentation, TransferLearning

Abstract: We present a novel approach of 2D to 3D transfer learning based on mapping pre-trained 2D convolutional neural network weights into planar 3D kernels. The method is validated by the …

Filter by

Categories

Tags