Home /
Research
Showing 865 - 870 / 904
COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering
FarhadMoghimifar, LizhenQu, YueZhuo....
Published date-11/02/2020
QuestionAnswering
Commonsense reasoning refers to the ability of evaluating a social situation and acting accordingly. Identification of the implicit causes and effects of a social context is the driving capability which …
Multi-Agent Reinforcement Learning for Persistent Monitoring
JingxiChen, AmrishBaskaran, ZhongshunZhang....
Published date-11/02/2020
Multi-agentReinforcementLearning
The Persistent Monitoring (PM) problem seeks to find a set of trajectories (or controllers) for robots to persistently monitor a changing environment. Each robot has a limited field-of-view and may …
ABNIRML: Analyzing the Behavior of Neural IR Models
SeanMacAvaney, SergeyFeldman, NazliGoharian....
Published date-11/02/2020
LanguageModelling
Numerous studies have demonstrated the effectiveness of pretrained contextualized language models such as BERT and T5 for ad-hoc search. However, it is not well-understood why these methods are so effective, …
IOS: Inter-Operator Scheduler for CNN Acceleration
YaoyaoDing, LigengZhu, ZhihaoJia....
Published date-11/02/2020
To accelerate CNN inference, existing deep learning frameworks focus on optimizing intra-operator parallelization. However, a single operator can no longer fully utilize the available parallelism given the rapid advances in …
Learning in the Wild with Incremental Skeptical Gaussian Processes
AndreaBontempelli, StefanoTeso, FaustoGiunchiglia....
Published date-11/02/2020
GaussianProcesses
The ability to learn from human supervision is fundamental for personal assistants and other interactive applications of AI. Two central challenges for deploying interactive learners in the wild are the …
Max-value Entropy Search for Multi-objective Bayesian Optimization with Constraints
DanielFernández-Sánchez, EduardoC.Garrido-Merchán, DanielHernández-Lobato....
Published date-11/02/2020
We present MESMOC, a Bayesian optimization method that can be used to solve constrained multi-objective problems when the objectives and the constraints are expensive to evaluate. MESMOC works by minimizing …