Home /

Research

Showing 715 - 720 / 904

Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification


Authors:  AgusSudjianto, WilliamKnauth, RahulSingh....
Published date-11/08/2020

Abstract: The deep neural networks (DNNs) have achieved great success in learning complex patterns with strong predictive power, but they are often thought of as "black box" models without a sufficient …

Pathwise Conditioning of Gaussian Processes


Authors:  JamesT.Wilson, ViacheslavBorovitskiy, AlexanderTerenin....
Published date-11/08/2020
Tasks:  GaussianProcesses

Abstract: As Gaussian processes are integrated into increasingly complex problem settings, analytic solutions to quantities of interest become scarcer and scarcer. Monte Carlo methods act as a convenient bridge for connecting …

NLP-CIC @ PRELEARN: Mastering prerequisites relations, from handcrafted features to embeddings


Authors:  JasonAngel, SegunTaofeekAroyehun, AlexanderGelbukh....
Published date-11/07/2020

Abstract: We present our systems and findings for the prerequisite relation learning task (PRELEARN) at EVALITA 2020. The task aims to classify whether a pair of concepts hold a prerequisite relation …

Deep traffic light detection by overlaying synthetic context on arbitrary natural images


Authors:  JeanPabloVieiradeMello, LucasTabelini, RodrigoF.Berriel....
Published date-11/07/2020
Tasks:  AutonomousDriving

Abstract: Deep neural networks come as an effective solution to many problems associated with autonomous driving. By providing real image samples with traffic context to the network, the model learns to …

Implementing Behavior Trees using Three-Valued Logic


Authors:  ThibauddeSouza....
Published date-11/07/2020

Abstract: With consideration to behavior trees and their relevance to planning and control, within and without game development, the distinction between stateful and stateless models is discussed; a three-valued logic bridging …

DG: A program analysis library


Authors:  MarekChalupa....
Published date-11/07/2020

Abstract: DG is a C++ library providing elements for building program analysis tools. Its main components are a points-to analysis, a data dependence analysis, a control dependence analysis and an analysis …

Filter by

Categories

Tags