547 Hits in 12.0 sec

Self-Paced Deep Regression Forests with Consideration on Underrepresented Examples [article]

Lili Pan, Shijie Ai, Yazhou Ren, Zenglin Xu
2020 arXiv   pre-print
To this end, this paper proposes a new deep discriminative model--self-paced deep regression forests with consideration on underrepresented examples (SPUDRFs).  ...  Deep discriminative models (e.g. deep regression forests, deep neural decision forests) have achieved remarkable success recently to solve problems such as facial age estimation and head pose estimation  ...  Specifically, we focus on deep regression forests (DRFs), a typical discriminative method, and propose self-paced deep regression forests with consideration on underrepresented examples (SPUDRFs).  ... 
arXiv:2004.01459v4 fatcat:qawk4t3l35fenb5wesfjg4v4h4

Self-Paced Deep Regression Forests with Consideration of Ranking Fairness [article]

Lili Pan, Mingming Meng, Yazhou Ren, Yali Zheng, Zenglin Xu
2022 arXiv   pre-print
Deep discriminative models (DDMs), e.g. deep regression forests and deep decision forests, have been extensively studied recently to solve problems such as facial age estimation, head pose estimation,  ...  First, this is more consistent with the cognitive process of human beings. Second, noisy as well as underrepresented examples can be distinguished by virtue of previously learned knowledge.  ...  ACKNOWLEDGMENT The authors would like to thank Jiabei Zeng of the Institute of Computing Technology, Chinese Academy on Sciences, for the valuable advice on the gaze estimation experiments.  ... 
arXiv:2112.06455v8 fatcat:im5zkwvrkbecrdqwwfj67gaetq

Educational Anomaly Analytics: Features, Methods, and Challenges

Teng Guo, Xiaomei Bai, Xue Tian, Selena Firmin, Feng Xia
2022 Frontiers in Big Data  
With the popularity of educational management systems and the rise of online education during the prevalence of COVID-19, a large amount of educational data is available online and offline, providing an  ...  We focus on the following five types of research that received the most attention: course failure prediction, dropout prediction, mental health problems detection, prediction of difficulty in graduation  ...  Temporal analysis for dropout prediction using self-regulated learning strategies in self-paced moocs. Comput.  ... 
doi:10.3389/fdata.2021.811840 pmid:35098114 pmcid:PMC8795666 fatcat:2cejzd6kkvesbly6ytxfy5lb2e

Toward Urban Water Security: Broadening the Use of Machine Learning Methods for Mitigating Urban Water Hazards

Melissa R. Allen-Dumas, Haowen Xu, Kuldeep R. Kurte, Deeksha Rastogi
2021 Frontiers in Water  
For example, risks associated with flood, drought and water quality can be identified using genetic algorithms, artificial neural networks, support vector machines, random forests, and other types of regression  ...  forest analysis discussed in section 2.2.1) and linear regression.  ... 
doi:10.3389/frwa.2020.562304 fatcat:4g4x5qsljva63fzfibqyjhsdsi

Who Continues in a Series of Lifelong Learning Courses?

Sami Sarsa, Arto Hellas, Juho Leinonen
2022 Proceedings of the 27th ACM Conference on on Innovation and Technology in Computer Science Education Vol. 1  
For example, participants often have more varied motivations and aspirations as well as more varied educational backgrounds.  ...  Our study provides further evidence that lifelong learning benefits most the already educated part of the population with prior knowledge and high motivation.  ...  Models used for regression in this study comprise Linear regression, and Bayesian Ridge regression as linear models, Random forest as non-linear regression model, and a dummy regressor Mean regression  ... 
doi:10.1145/3502718.3524752 fatcat:keez5io26nd2ndjbjbccbfapby

Algorithmic Fairness in Education [article]

René F. Kizilcec, Hansol Lee
2021 arXiv   pre-print
In this introduction to algorithmic fairness in education, we draw parallels to prior literature on educational access, bias, and discrimination, and we examine core components of algorithmic systems (  ...  Their interest in algorithmic fairness focused on protected groups defined based on students' learning speed to evaluate if the self-paced system discriminates against students from either group.  ...  For instance, a (penalized) linear regression algorithm might be used to learn a model for a continuous outcome like cumulative GPA, while a random forest algorithm might be used to learn a model for a  ... 
arXiv:2007.05443v3 fatcat:x7m3f56ybza65flnaidv3onht4

Synergies of Learning Analytics and Learning Design: A Systematic Review of Student Outcomes

Marion Blumenstein
2020 Journal of Learning Analytics  
Large positive effects on student outcomes were found in LDs that fostered socio-collaborative and independent learning skills.  ...  Despite the growing potential of LA in higher education (HE), the benefits are not yet convincing to the practitioner, in particular aspects of aligning LA data with LD toward desired learning outcomes  ...  Further, I would like to acknowledge Jessica McLay for recalculating the effect sizes and Daniel Barnett for preparing the Forest Plot (both University of Auckland Statistical Consulting Centre), and also  ... 
doi:10.18608/jla.2020.73.3 fatcat:kqpmi5d7sfe27lv6u43il7676i

State of Climate Action 2021: Systems Transformations Required to Limit Global Warming to 1.5°C

Sophie Boehm, Katie Lebling, Kelly Levin, Hanna Fekete, Joel Jaeger, Richard Waite, Anna Nilsson, Joe Thwaites, Ryan Wilson, Andreas Geiges, Clea Schumer, Maggie Dennis (+12 others)
2021 World Resources Institute  
Of the 40 indicators assessed, none are on track to reach 2030 targets.  ...  Finance for climate action, for example, must increase nearly 13-fold to meet the estimated need in 2030.  ...  A recent report on humid primary tropical forests, for example, found that losses in these forests resulted in 2.64 Gt of CO 2 e in the year 2020 alone (WRI 2021d).  ... 
doi:10.46830/wrirpt.21.00048 fatcat:7v2cfy3q55c3zpkoc22hwx3txy

Machine-learning-based Brokers for Real-time Classification of the LSST Alert Stream

Gautham Narayan, Tayeb Zaidi, Monika D. Soraisam, Zhe Wang, Michelle Lochner, Thomas Matheson, Abhijit Saha, Shuo Yang, Zhenge Zhao, John Kececioglu, Carlos Scheidegger, Richard T. Snodgrass (+11 others)
2018 Astrophysical Journal Supplement Series  
The Arizona-NOAO Temporal Analysis and Response to Events System (ANTARES) is one such broker.  ...  While several similar algorithms have proven themselves in simulations, we validate their performance on real observations for the first time.  ...  Example Gaussian process regression models are shown in Figure 8 for an SNPhotCC Ia as well as a periodic variable star.  ... 
doi:10.3847/1538-4365/aab781 fatcat:lpjliwrpkncjtam4v2puqoksdq

Trustworthy AI: From Principles to Practices [article]

Bo Li, Peng Qi, Bo Liu, Shuai Di, Jingen Liu, Jiquan Pei, Jinfeng Yi, Bowen Zhou
2022 arXiv   pre-print
In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems.  ...  The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it.  ...  We also thank Yu He, Wenhan Xu, Xinyuan Shan, Chenliang Wang, Peng Liu, Jingling Fu, Baicun Zhou, Hongbao Tian and Qili Wang for their assistance with the experiment in the appendix.  ... 
arXiv:2110.01167v2 fatcat:2u7hqdrfujc5lbcsmwpmxxsd74

Restoration of Visitors through Nature-Based Tourism: A Systematic Review, Conceptual Framework, and Future Research Directions

Mengyuan Qiu, Ji Sha, Noel Scott
2021 International Journal of Environmental Research and Public Health  
The findings provide a theoretical perspective on the consideration of nature-based tourism as a public-wellness product worldwide, and the study provides recommendations for future research in a COVID  ...  This study aimed to explore how visitors achieve restoration through nature by analyzing published literature on tourism.  ...  Our understanding of the restoration of visitors with different demographic cohorts in various parts of the world is limited because some specific groups are underrepresented.  ... 
doi:10.3390/ijerph18052299 pmid:33652652 pmcid:PMC7956513 fatcat:dhn4vympsvhwjmg3ms3gckd6ra

Long-Term Ecological Research in a Human-Dominated World

G. Philip Robertson, Scott L. Collins, David R. Foster, Nicholas Brokaw, Hugh W. Ducklow, Ted L. Gragson, Corinna Gries, Stephen K. Hamilton, A. David McGuire, John C. Moore, Emily H. Stanley, Robert B. Waide (+1 others)
2012 BioScience  
and to engage with decisionmakers in framing major directions for research.  ...  The network's potential for tackling emergent continent-scale questions such as cryosphere loss and landscape change is becoming increasingly apparent on the basis of a capacity to combine long-term observations  ...  For example, the ability of the HBRF Science Links projects to assess the impacts of air-quality regulations and the extent on Rural Alaska Self-Reliance, a collaboration to implement community visions  ... 
doi:10.1525/bio.2012.62.4.6 fatcat:tpgigruozzcdpkthe3kbynkvre

Ecology and conservation of ginseng (Panax quinquefolius) in a changing world

James B. McGraw, Anne E. Lubbers, Martha Van der Voort, Emily H. Mooney, Mary Ann Furedi, Sara Souther, Jessica B. Turner, Jennifer Chandler
2013 Annals of the New York Academy of Sciences  
American ginseng (Panax quinquefolius L.) is an uncommon to rare understory plant of the eastern deciduous forest.  ...  Harvesting to supply the Asian traditional medicine market made ginseng North America's most harvested wild plant for two centuries, eventually prompting a listing on CITES Appendix II.  ...  Demographic simulations show that a stewardshiporiented harvester, who complies with these later season onset dates, self-limits harvest intensity, and optimally plants ginseng seeds 2 cm deep at the time  ... 
doi:10.1111/nyas.12032 pmid:23398402 fatcat:jbyf34qhwrbn7b3meazcatryze

Artificial Intelligence: Research Impact on Key Industries; the Upper-Rhine Artificial Intelligence Symposium (UR-AI 2020) [article]

Andreas Christ, Franz Quint
2020 arXiv   pre-print
Recent work shows considerable progress on learning model-free behaviors using genetic learning [6] for kicking with toes and deep reinforcement learning [7, 8, 9] for walking without toe joints.  ...  Again Random Forests is the algorithm with the best metrics. Linear regression and SVM are comparable in terms of while SGD is worse but shows good RSME values.  ... 
arXiv:2010.16241v1 fatcat:y6lc2dmlyvh55bw2ytfbf7hwta

Cretaceous vegetation: the macrofossil record [chapter]

J. G. Douglas
2017 History of the Australian Vegetation: Cretaceous to Recent  
George, combined with modem eucalypt distributions, show that open eucalypt woodlands were very widespread across the Bassian Plain and along the Western Slopes as far as Queensland.  ...  This is done with considerable misgivings.  ...  The evidence for warm marine conditions is consistent with the interval being one of considerable humidity.  ... 
doi:10.20851/australian-vegetation-09 fatcat:tee5whxovve4booagkiybxii6i
« Previous Showing results 1 — 15 out of 547 results