Home /

Research

Showing 493 - 498 / 897

Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?


Authors:  GuoqiangWu, JunZhu....
Published date-11/16/2020
Tasks:  Multi-LabelClassification

Abstract: Various evaluation measures have been developed for multi-label classification, including Hamming Loss (HL), Subset Accuracy (SA) and Ranking Loss (RL). However, there is a gap between empirical results and the …

NLPGym -- A toolkit for evaluating RL agents on Natural Language Processing Tasks


Authors:  RajkumarRamamurthy, RafetSifa, ChristianBauckhage....
Published date-11/16/2020
Tasks:  Multi-LabelClassification, OpenAIGym, QuestionAnswering

Abstract: Reinforcement learning (RL) has recently shown impressive performance in complex game AI and robotics tasks. To a large extent, this is thanks to the availability of simulated environments such as …

The Person Index Challenge: Extraction of Persons from Messy, Short Texts


Authors:  MarkusSchröder, ChristianJilek, MichaelSchulze....
Published date-11/16/2020

Abstract: When persons are mentioned in texts with their first name, last name and/or middle names, there can be a high variation which of their names are used, how their names …

Enforcing robust control guarantees within neural network policies


Authors:  PriyaL.Donti, MelroseRoderick, MahyarFazlyab....
Published date-11/16/2020

Abstract: When designing controllers for safety-critical systems, practitioners often face a challenging tradeoff between robustness and performance. While robust control methods provide rigorous guarantees on system stability under certain worst-case disturbances, …

Learning Associative Inference Using Fast Weight Memory


Authors:  ImanolSchlag, TsendsurenMunkhdalai, JürgenSchmidhuber....
Published date-11/16/2020
Tasks:  LanguageModelling, MetaReinforcementLearning

Abstract: Humans can quickly associate stimuli to solve problems in novel contexts. Our novel neural network model learns state representations of facts that can be composed to perform such associative inference. …

Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment


Authors:  HaoranSun, WenqiangPu, MingheZhu....
Published date-11/16/2020
Tasks:  ContinualLearning, fairness

Abstract: There has been a growing interest in developing data-driven and in particular deep neural network (DNN) based methods for modern communication tasks. For a few popular tasks such as power …

Filter by

Categories

Tags