Filters








204,180 Hits in 4.5 sec

Uncertain Reasoning and Learning for Feature Grouping

ZuWhan Kim, Ramakant Nevatia
1999 Computer Vision and Image Understanding  
Hierarchical perceptual organization is needed for 3-D object detection and description. The hypothesize and verify paradigm offers one approach to this task.  ...  Hypotheses are generated from simpler features satisfying some possibly task dependent properties. More global evidence is used to verify and assign a confidence measure to the hypotheses.  ...  The main reason for not using these hypotheses in learning is that the evidence for them can be highly variable.  ... 
doi:10.1006/cviu.1999.0803 fatcat:ox5crjlrmjggfg45qctbfri32q

Feature-based versus category-based induction with uncertain categories

Oren Griffiths, Brett K. Hayes, Ben R. Newell
2012 Journal of Experimental Psychology. Learning, Memory and Cognition  
Previous research has suggested that when feature inferences have to be made about an instance whose category membership is uncertain, feature-based inductive reasoning is used to the exclusion of categorybased  ...  The present experiments examined the conditions that drive feature-based and category-based strategies in induction under category uncertainty.  ...  Decision-Only Tasks: Implications for Category Learning and Exemplar Availability Another characteristic feature of uncertain induction tasks, as opposed to induction tasks in which categorization is certain  ... 
doi:10.1037/a0026038 pmid:22060277 fatcat:haqcl3zx3bhhzezqtsqpw6s2aa

Benefits and challenges of real-time uncertainty detection and adaptation in a spoken dialogue computer tutor

Kate Forbes-Riley, Diane Litman
2011 Speech Communication  
Our adaptive system detects uncertainty in each student turn via a model that combines a machine learning approach with hedging phrase heuristics; the learned model uses acoustic-prosodic and lexical features  ...  The adaptive system varies its content based on the automatic uncertainty and correctness labels for each turn.  ...  Acknowledgments This work is funded by National Science Foundation (NSF) awards #0914615 and #0631930. We thank Pam Jordan and the ITSPOKE Group for their  ... 
doi:10.1016/j.specom.2011.02.006 fatcat:qqz3nxnkrneqxgkese7ewxrfte

Suppressing Uncertainties for Large-Scale Facial Expression Recognition

Kai Wang, Xiaojiang Peng, Jianfei Yang, Shijian Lu, Yu Qiao
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
mechanism to modify the labels of these samples in the lowest-ranked group.  ...  To address this problem, this paper proposes a simple yet efficient Self-Cure Network (SCN) which suppresses the uncertainties efficiently and prevents deep networks from over-fitting uncertain facial  ...  According to the feature type, they can be grouped into engineered features and learning-based features.  ... 
doi:10.1109/cvpr42600.2020.00693 dblp:conf/cvpr/WangPYL020 fatcat:wfvs3yzksfhjvmwhocobzsl4oi

Suppressing Uncertainties for Large-Scale Facial Expression Recognition [article]

Kai Wang, Xiaojiang Peng, Jianfei Yang, Shijian Lu, Yu Qiao
2020 arXiv   pre-print
mechanism to modify the labels of these samples in the lowest-ranked group.  ...  To address this problem, this paper proposes a simple yet efficient Self-Cure Network (SCN) which suppresses the uncertainties efficiently and prevents deep networks from over-fitting uncertain facial  ...  First, it may result in over-fitting on the uncertain samples which may be mislabeled. Second, it is harmful for a model to learn useful facial expression features.  ... 
arXiv:2002.10392v2 fatcat:urzvtho7ezbn5klnp3tfxqcaqu

Predictive Analytic on Human Resource Department Data Based on Uncertain Numeric Features Classification

Asrul Huda, Noper Ardi
2021 International Journal of Interactive Mobile Technologies  
So we develop a way to solve the problem using uncertain Numeric features classification on it. The accuracy of the result is depended on the amount and effectiveness of the training sets.  ...  Business Intelligence is very popular and useful for a better understanding of business progress these days, and there are many different methods or tools being used in Business Intelligence.  ...  The complete data for those five uncertain numeric features is shown in the table 1 below.  ... 
doi:10.3991/ijim.v15i08.20907 doaj:aa0a3808229342f990bfb0b6c995d091 fatcat:6ztjyke4efgylmrjrnzoqxzt5a

Bayesian Convolutional Neural Networks for Seven Basic Facial Expression Classifications [article]

Yuan Tai, Yihua Tan, Wei Gong, Hailan Huang
2021 arXiv   pre-print
group.  ...  Through testing on the FER2013 test set, we achieved 71.5% and 73.1% accuracy in PublicTestSet and PrivateTestSet, respectively.  ...  Performance Testing In experiments we choose ResNet18 for feature extraction of images, and form a lightweight and effective ResNet18_BNN network under the framework of Bayesian neural network.  ... 
arXiv:2107.04834v2 fatcat:ra6sqgy2vfghnoxc3l6gfnz27m

Induction with uncertain categories: When do people consider the category alternatives?

Brett K. Hayes, Ben R. Newell
2009 Memory & Cognition  
However, the prevalence of such single-category reasoning was greatly reduced by highlighting the costs of neglecting nontarget alternatives and by asking for inferences before categorization decisions  ...  Participants were shown two categories and a novel exemplar with a feature that indicated that the exemplar was more likely to belong to one category (target) than to the other (nontarget).  ...  The two groups of planets are called Class E and Class K. To help you learn each class we will describe some of the characteristics of eight Class E planets and eight Class K planets.  ... 
doi:10.3758/mc.37.6.730 pmid:19679854 fatcat:al3f6t2i6jawbgipxc2ywjs4ju

Page 38 of College and University Vol. 28, Issue 1 [page]

1952 College and University  
38 > COLLEGE AND UNIVERSITY, OCTOBER, 1952 clarify. the relation between what the student is learning and his pre- ferred vocation have no doubt discovered a powerful tool for motivat- ing the learning  ...  certain that he would pursue his first choice, (3) many things stood in the way, so his first choice was somewhat tenta- tive, and (4) the student was very uncertain about his possibilities for pursuing  ... 

The effect of uncertainty on learning in game-like environments

Erol Ozcelik, Nergiz Ercil Cagiltay, Nese Sahin Ozcelik
2013 Computers & Education  
However, few research studies have been conducted to establish principles based on empirical research for designing engaging and entertaining games so as to improve learning.  ...  Learning is more fun and appealing in digital educational games and, as a result, it may become more effective.  ...  standard deviations for uncertain and certain groups on prior knowledge test and post-test.  ... 
doi:10.1016/j.compedu.2013.02.009 fatcat:6tyvaehoibfmnhsizmiedaxi44

Multiple kernel active learning for image classification

Jingjing Yang, Yuanning Li, Yonghong Tian, Lingyu Duan, Wen Gao
2009 2009 IEEE International Conference on Multimedia and Expo  
Uncertain samples are first clustered into groups, and then informative samples are consequently selected via inter-group and intra-group competitions.  ...  LA-AL adopts a top-down (or global-local) strategy for locating and searching informative samples.  ...  However, the computational complexity of MKL is very high for two major reasons: 1).  ... 
doi:10.1109/icme.2009.5202555 dblp:conf/icmcs/YangLTDG09 fatcat:uosvk3z63fal3asz4dpmkzdulm

Survivability of Cloud Databases - Factors and Prediction

Jose Picado, Willis Lang, Edward C. Thayer
2018 Proceedings of the 2018 International Conference on Management of Data - SIGMOD '18  
Service providers such as Microsoft try to understand and characterize these behaviors in order to improve the quality of their service, provide new features for customers, and/or increase the efficiency  ...  Given the large and diverse relational database population that Azure SQL DB has, we present a large-scale survivability study of our service and identify some factors that can demonstrably help predict  ...  For business and privacy reasons [4] , and discussion length, we are not able to examine and/or discuss all possible features at our disposal, but we present some intuitive features that may be predictive  ... 
doi:10.1145/3183713.3190651 dblp:conf/sigmod/PicadoLT18 fatcat:rv2yemwh5ngcxh667ld272mrtq

Page 79 of Journal of Research and Practice in Information Technology Vol. 24, Issue 2 [page]

1992 Journal of Research and Practice in Information Technology  
Commercial tools for expert system development offer only primitive features for learning and reasoning in the presence of uncertainty.  ...  Other uncertain reasoning papers discuss Depster-Shafer theory, INFERNO-style reasoning, non- monotonic reasoning and possibilistic reasoning.  ... 

Implementation of Four-Tier Multiple-Choice Instruments Based on the Partial Credit Model in Evaluating Students' Learning Progress

Lukman Abdul, Syukrul Hamdi*, Masrid Pikoli, Romario Abdullah, Citra Panigoro
2021 European Journal of Educational Research  
All in all, the research regarded that the diagnostic information was necessary for teachers in prospective development of learning strategies and evaluation of science learning.  ...  The result revealed that the integration of 4TMC test and Partial-Credit Model was effective to be treated as the instrument to measure students' learning progress.  ...  Acknowledgments The researchers would like to express their gratitude towards the Directorate of Research and Community Service, Ministry of Research and Technology of Republic of Indonesia, for the financial  ... 
doi:10.12973/eu-jer.10.2.825 fatcat:3hyh32habbd7xm4wjncwvsduje

Transfer Learning in Collaborative Filtering with Uncertain Ratings

Weike Pan, Evan Xiang, Qiang Yang
2021 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In particular, we integrate auxiliary data of uncertain ratings as additional constraints in the target matrix factorization problem, and learn an expected rating value for each uncertain rating automatically  ...  In this paper, we propose an efficient transfer learning solution for collaborative filtering, known as {\em transfer by integrative factorization} (TIF), to leverage such auxiliary uncertain ratings to  ...  Acknowledgments We thank the support of Hong Kong RGC GRF Projects 621010 and 621211.  ... 
doi:10.1609/aaai.v26i1.8197 fatcat:2whpkjigqngptn73rcihz5jzge
« Previous Showing results 1 — 15 out of 204,180 results