420,209 Hits in 4.9 sec

Learning Unknown Event Models

Matthew Molineaux, David Aha
models for surprising events.  ...  We investigate approaches for situated agents to detect surprises, discriminate among different forms of surprise, and hypothesize new models for the unknown events that surprised them.  ...  FOOLMETWICE learns these models by detecting unknown events, generalizing event preconditions, and hypothesizing an event model.  ... 
doi:10.1609/aaai.v28i1.8751 fatcat:hppllpewrzhnfpmitr7i37pp7a

Gerçek Ortamlarda Artımlı Öğrenme ile Gerçek Zamanlı İşitsel Sahne Analizi

Barış BAYRAM, Gökhan İNCE
2020 European Journal of Science and Technology  
The learning process is investigated by conducting a variety of experiments to evaluate the performance of Unknown Event Detection (UED), Acoustic Event Recognition (AER), and continual learning using  ...  Continual learning for scene analysis is a continuous process to incrementally learn distinct events, actions, and even noise models from past experiences using different sensory modalities.  ...  Subsequently, continual learning is achieved to learn knowledge about a known event by retraining, or unknown event by adapting its knowledge into the model.  ... 
doi:10.31590/ejosat.779710 fatcat:5i2rwdh23ndgzkr7dy4redk7my

Demand learning and dynamic pricing for multi-version products

Guillermo Gallego, Masoud Talebian
2010 Journal of Revenue and Pricing Management  
A major source of motivation for this paper is the case of demand learning in the event management industry, where event tickets are priced over time and demand is uncertain.  ...  This is known as demand learning.  ...  The reason behind this limitation may be the mathematical complications that arise from the combination of learning two unknowns.  ... 
doi:10.1057/rpm.2010.36 fatcat:conmvrvmqnbmhcff5wccarevr4

Adapting machine learning techniques to censored time-to-event health record data: A general-purpose approach using inverse probability of censoring weighting

David M. Vock, Julian Wolfson, Sunayan Bandyopadhyay, Gediminas Adomavicius, Paul E. Johnson, Gabriela Vazquez-Benitez, Patrick J. O'Connor
2016 Journal of Biomedical Informatics  
Most machine learning approaches to the problem have been relatively ad hoc; for example, common approaches for handling observations in which the event status is unknown include 1) discarding those observations  ...  , and generalized additive models.  ...  with unknown event statuses or adapting specific machine learning tools to censored, time-to-event data.  ... 
doi:10.1016/j.jbi.2016.03.009 pmid:26992568 pmcid:PMC4893987 fatcat:ikux2my3drhpdbectlx53xtymq

Actor Critic Deep Reinforcement Learning for Neural Malware Control

Yu Wang, Jack Stokes, Mady Marinescu
Recent research uses a deep reinforcement learning (DRL) model employing a Deep Q-Network (DQN) to learn when to halt the emulation of a file.  ...  In terms of execution speed (evaluated by the halting decision), the new model halts the execution of unknown files by up to 2.5% earlier than the DQN model and 93.6% earlier than the heuristics.  ...  deep reinforcement learning model.  ... 
doi:10.1609/aaai.v34i01.5449 fatcat:dizfmtdvivglzlo2by7vaosqqq

Research on Running Time Behavior Analyzing and Trend Predicting of Modern Distributed Software

Junfeng Man, Zhicheng Wen, Changyun Li, Xiangbing Wen
2009 Journal of Computers  
We use hierarchical Dirichlet process and infinite hidden Markov model to converge monitored interface data to determine unknown events, and learn behavior patterns from event sequences including unknown  ...  We adopt Viterbi algorithm of hidden Markov model to analyze optimal sequences of interactive events, which help to determine good and evil of current behaviors.  ...  The diagram of identifying and learning unknown events is showed in Fig. 2 .  ... 
doi:10.4304/jcp.4.8.747-754 fatcat:wytzjudca5fnpo6usx2wnzebwi

Active Management of Operational Risk in the Regimes of the "Unknown": What Can Machine Learning or Heuristics Deliver?

Udo Milkau, Jürgen Bott
2018 Risks  
Acknowledgments: The authors thank Rudi Schäfer, Frankfurt, and unknown referees for valuable comments and discussion.  ...  For what regime of the "unknown"-rare events or even unforeseen event types-could machine learning be applied? 3.  ...  Machine Learning It the "Unknown Unknown" For a discussion of the domain of "once in a lifetime events," it is important to recall the scope of the business.  ... 
doi:10.3390/risks6020041 fatcat:yjrahx6vt5fptf26uroptipbpa

Semi-supervised based Unknown Attack Detection in EDR Environment

2020 KSII Transactions on Internet and Information Systems  
In the future, it is expected that the proposed model will be applied to EDR technology to form a secure endpoint environment and reduce time and labor costs to effectively detect unknown attacks.  ...  In this paper, we propose a technique that detects an unknown attack using an event log without prior knowledge, although the initial response failed with anti-virus.  ...  AutoEncoder based unknown attack model The collected endpoint log data is based on unsupervised learning because no label exists.  ... 
doi:10.3837/tiis.2020.12.016 fatcat:no6o5drfejarng7d6slm4egixi

Inter-modality mapping in robot with recurrent neural network

Tetsuya Ogata, Shun Nishide, Hideki Kozima, Kazunori Komatani, Hiroshi G. Okuno
2010 Pattern Recognition Letters  
Keepon behaved appropriately not only from learned events but also from unknown events and generated various sounds in accordance with observed motions. the robot to handle all the data simultaneously,  ...  A recurrent neural network model with parametric bias, which has good generalization ability, is used as a learning model.  ...  Keepon behaved appropriately not only for learned events but also for unknown events. It also generated sounds appropriate for observed motions.  ... 
doi:10.1016/j.patrec.2010.05.002 fatcat:kp735kf2lvfbza5varedelrc74

Learning about risk: Machine learning for risk assessment

Nicola Paltrinieri, Louise Comfort, Genserik Reniers
2019 Safety Science  
deal with unexpected events and provide the right support to enable risk management.  ...  Through this work, we suggest a risk assessment approach based on machine learning.  ...  Acknowledgements This research was supported by the project Lo-Risk ("Learning about Risk"), supported by the Norwegian University of Science and Technology -NTNU (Onsager fellowship).  ... 
doi:10.1016/j.ssci.2019.06.001 fatcat:qrqzoaogp5fcjoo3nje3qbdyua

Stream-Based Active Unusual Event Detection [chapter]

Chen Change Loy, Tao Xiang, Shaogang Gong
2011 Lecture Notes in Computer Science  
It adaptively combines multiple active learning criteria to achieve (i) quick discovery of unknown event classes and (ii) refinement of classification boundary.  ...  We present a new active learning approach to incorporate human feedback for on-line unusual event detection.  ...  Discover unknown event classes -As can be seen from Figure 4 , like showed the best performance in discovering unknown event classes in both datasets.  ... 
doi:10.1007/978-3-642-19315-6_13 fatcat:ry25zkr3ajdxdcirrfzwdhjyme

Zero-bias Deep Neural Network for Quickest RF Signal Surveillance [article]

Yongxin Liu, Yingjie Chen, Jian Wang, Shuteng Niu, Dahai Liu, Houbing Song
2021 arXiv   pre-print
considering incremental learning and decision fairness.  ...  In this paper, we provide a deep learning framework for RF signal surveillance.  ...  For unknown event detection, the most intuitive way is to use statistical models to generate likelihood metrics and then use thresholds to distinguish whether an input is within the learned knowledge domain  ... 
arXiv:2110.05797v1 fatcat:6oiucnqrjnbi7dtygbmjn4yq34

Do Many Models Make Light Work? Evaluating Ensemble Solutions for Improved Rumor Detection

Younghwan Kim, Huy Kang Kim, Hyoungshick Kim, Jin B. Hong
2020 IEEE Access  
unknown rumor events.  ...  To test the detection of unknown rumor events, we train the models using other rumor event data (i.e., to test unknown rumor event Ferguson, the training data will consist of all other events but excluding  ... 
doi:10.1109/access.2020.3016664 fatcat:u7wjuk2gvvagblvybfkwixvefe

Modular Supervisory Synthesis for Unknown Plant Models Using Active Learning

Fredrik Hagebring, Ashfaq Farooqui, Martin Fabian
2020 IFAC-PapersOnLine  
This paper proposes an approach to synthesize a modular discrete-event supervisor to control a plant, the behavior model of which is unknown, so as to satisfy given specifications.  ...  However, there exist active learning algorithms that can be used to infer a discrete model of the plant from a simulation.  ...  model of which is unknown, so as to satisfy given specifications.  ... 
doi:10.1016/j.ifacol.2021.04.032 fatcat:6lupyzbsfraxzln4wdtrjm674i

Active learning for automatic classification of software behavior

James F. Bowring, James M. Rehg, Mary Jean Harrold
2004 Software engineering notes  
We present a technique that models program executions as Markov models, and a clustering method for Markov models that aggregates multiple program executions into effective behavior classifiers.  ...  In contrast, we explore an active-learning paradigm for behavior classification. In active learning, the classifier is trained incrementally on a series of labeled data elements.  ...  Their models are built once use batch learning whereas we demonstrate the advantages of active learning.  ... 
doi:10.1145/1013886.1007539 fatcat:ai2wasvlxzbffkslip6syz2f7q
« Previous Showing results 1 — 15 out of 420,209 results