Home /
Research
Showing 337 - 342 / 904
Stable Weight Decay Regularization
ZekeXie, IsseiSato, MasashiSugiyama....
Published date-11/23/2020
Weight decay is a popular regularization technique for training of deep neural networks. Modern deep learning libraries mainly use $L_{2}$ regularization as the default implementation of weight decay. \citet{loshchilov2018decoupled} demonstrated …
HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms
MahmoudAfifi, MarcusA.Brubaker, MichaelS.Brown....
Published date-11/23/2020
ImageGeneration
While generative adversarial networks (GANs) can successfully produce high-quality images, they can be challenging to control. Simplifying GAN-based image generation is critical for their adoption in graphic design and artistic …
Reachable Polyhedral Marching (RPM): A Safety Verification Algorithm for Robotic Systems with Deep Neural Network Components
JosephA.Vincent, MacSchwager....
Published date-11/23/2020
We present a method for computing exact reachable sets for deep neural networks with rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety analysis of …
Siamese Tracking with Lingual Object Constraints
MaximilianFiltenborg, EfstratiosGavves, DeepakGupta....
Published date-11/23/2020
ObjectTracking, QuestionAnswering, VideoSummarization, VisualObjectTracking, VisualQuestionAnswering
Classically, visual object tracking involves following a target object throughout a given video, and it provides us the motion trajectory of the object. However, for many practical applications, this output …
Discovering Causal Structure with Reproducing-Kernel Hilbert Space $ε$-Machines
NicolasBrodu, JamesP.Crutchfield....
Published date-11/23/2020
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 …
Ensemble- and Distance-Based Feature Ranking for Unsupervised Learning
MatejPetković, DragiKocev, BlažŠkrlj....
Published date-11/23/2020
Clustering
In this work, we propose two novel (groups of) methods for unsupervised feature ranking and selection. The first group includes feature ranking scores (Genie3 score, RandomForest score) that are computed …