Home /
Research
Showing 493 - 498 / 897
Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?
GuoqiangWu, JunZhu....
Published date-11/16/2020
Multi-LabelClassification
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
RajkumarRamamurthy, RafetSifa, ChristianBauckhage....
Published date-11/16/2020
Multi-LabelClassification, OpenAIGym, QuestionAnswering
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
MarkusSchröder, ChristianJilek, MichaelSchulze....
Published date-11/16/2020
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
PriyaL.Donti, MelroseRoderick, MahyarFazlyab....
Published date-11/16/2020
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
ImanolSchlag, TsendsurenMunkhdalai, JürgenSchmidhuber....
Published date-11/16/2020
LanguageModelling, MetaReinforcementLearning
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
HaoranSun, WenqiangPu, MingheZhu....
Published date-11/16/2020
ContinualLearning, fairness
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 …