Home /
Research
Showing 643 - 648 / 904
Determining Question-Answer Plausibility in Crowdsourced Datasets Using Multi-Task Learning
RachelGardner, MayaVarma, ClareZhu....
Published date-11/10/2020
Multi-TaskLearning
Datasets extracted from social networks and online forums are often prone to the pitfalls of natural language, namely the presence of unstructured and noisy data. In this work, we seek …
STCNet: Spatio-Temporal Cross Network for Industrial Smoke Detection
YichaoCao, QingfeiTang, XiaoboLu....
Published date-11/10/2020
Industrial smoke emissions present a serious threat to natural ecosystems and human health. Prior works have shown that using computer vision techniques to identify smoke is a low cost and …
A Transfer Learning Approach for Dialogue Act Classification of GitHub Issue Comments
AyeshaEnayet, GitaSukthankar....
Published date-11/10/2020
DialogueActClassification, TransferLearning
Social coding platforms, such as GitHub, serve as laboratories for studying collaborative problem solving in open source software development; a key feature is their ability to support issue reporting which …
Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences
BowenBaker....
Published date-11/10/2020
Multi-agentReinforcementLearning
Multi-agent reinforcement learning (MARL) has shown recent success in increasingly complex fixed-team zero-sum environments. However, the real world is not zero-sum nor does it have fixed teams; humans face numerous …
Efficient and Transferable Adversarial Examples from Bayesian Neural Networks
MartinGubri, MaximeCordy, MikePapadakis....
Published date-11/10/2020
Deep neural networks are vulnerable to evasion attacks, i.e., carefully crafted examples designed to fool a model at test time. Attacks that successfully evade an ensemble of models can transfer …
What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes
HermanYau, ChrisRussell, SimonHadfield....
Published date-11/10/2020
We present a novel form of explanation for Reinforcement Learning, based around the notion of intended outcome. These explanations describe the outcome an agent is trying to achieve by its …