181 Hits in 9.0 sec

Deep Heterogeneous Face Recognition Networks Based on Cross-Modal Distillation and an Equitable Distance Metric

Christopher Reale, Hyungtae Lee, Heesung Kwon
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this work we present three methods to improve a deep convolutional neural network approach to near-infrared heterogeneous face recognition.  ...  We present the results of experiments of these methods on two widely used near-infrared heterogeneous face recognition datasets and compare them to the state-of-the-art.  ...  In this work, we focus on near-infrared (NIR) heterogeneous face recognition.  ... 
doi:10.1109/cvprw.2017.34 dblp:conf/cvpr/RealeLK17 fatcat:adyrmiyhibd5vf7gbph67epnwi

Urban growth and water access in sub-Saharan Africa: Progress, challenges, and emerging research directions

S. Dos Santos, E.A. Adams, G. Neville, Y. Wada, A. de Sherbinin, E. Mullin Bernhardt, S.B. Adamo
2017 Science of the Total Environment  
This paper contributes to interdisciplinary understanding of urban water supply by distilling and integrating relevant empirical knowledge on urban dynamics and water issues in SSA, focusing on progress  ...  Across the globe, nearly one in ten people is without access to an improved drinking water source.  ...  Acknowledgments and Data Material for this paper is drawn from the lead authors' research and expert contributions and discussions during a Population-Environment Research Network (PERN) cyberseminar on  ... 
doi:10.1016/j.scitotenv.2017.06.157 pmid:28704674 fatcat:4vt6lcbxmnadne2m3uwbhvacf4

Trustworthy Predictive Algorithms for Complex Forest System Decision-Making

Pushpendra Rana, Lav R. Varshney
2021 Frontiers in Forests and Global Change  
This review shows how domain-specific characteristics, such as system complexity, impose limits on using predictive algorithms in forest conservation and management.  ...  The expanding role of predictive algorithms is part of a broader movement toward using data-driven machine learning (ML) for modalities including images, natural language, speech.  ...  A variety of algorithms are used, including random forests and deep neural networks.  ... 
doi:10.3389/ffgc.2020.587178 fatcat:dvyqrvrinzeqvl2hkwy6kf3wnm

Chapter 17. OWI Research Considerations [chapter]

Christa Ehmann, Beth L. Hewett
2015 Foundational Practices of Online Writing Instruction  
--(Perspectives on writing) Includes bibliographical references and index. Description based on print version record and CIP data provided by publisher; resource not viewed.  ...  English language--Rhetoric--Study and teaching--Computer-assisted instruction. 2. Creative writing--Computer-assisted instruction. 3. Web-based instruction. I. Hewett, Beth L., editor of compilation.  ...  HYBRID AND FULLY-ONLINE OWCS For the purposes of this book, the term hybrid describes an environment where traditional, face-to-face instruction is combined with either distance-based or onsite computer-mediated  ... 
doi:10.37514/per-b.2015.0650.2.17 fatcat:t7jdzir2xnc4noegcuqsxrzvbm

On the Opportunities and Risks of Foundation Models [article]

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch (+102 others)
2021 arXiv   pre-print
Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization  ...  ., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.  ...  Fernando Pereira, Vinodkumar Prabhakaran, Colin Raffel, Marten van Schijndel, Ludwig Schmidt, Yoav Shoham, Madalsa Singh, Megha Srivastava, Jacob Steinhardt, Emma Strubell, Qian Yang, Luke Zettlemoyer, and  ... 
arXiv:2108.07258v2 fatcat:yktkv4diyrgzzfzqlpvaiabc2m

From Dependence to Causation [article]

David Lopez-Paz
2016 arXiv   pre-print
First, we develop a framework for the study of statistical dependence based on copulas and random features.  ...  Thus, understanding cause and effect is one step from machine learning towards machine reasoning and machine intelligence.  ...  distance metric learning", all of these eloquently reviewed in (Cunningham and Ghahramani, 2015) .  ... 
arXiv:1607.03300v1 fatcat:img5m23n5ncx5mfejgqkjft2ua

Tackling Climate Change with Machine Learning [article]

David Rolnick, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross, Nikola Milojevic-Dupont, Natasha Jaques, Anna Waldman-Brown, Alexandra Luccioni, Tegan Maharaj, Evan D. Sherwin, S. Karthik Mukkavilli (+6 others)
2019 arXiv   pre-print
Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help.  ...  We call on the machine learning community to join the global effort against climate change.  ...  Foundation and Carnegie Mellon University (SES-00949710), US Department of Energy contract DE-FG02-97ER25308, the Natural Sciences and Engineering Research Council of Canada, and the MIT Media Lab Consortium  ... 
arXiv:1906.05433v2 fatcat:ykmqsivkbfcazaz3wl5f7srula

IRRODL Volume 3, Number 2

Various Authors
2002 International Review of Research in Open and Distance Learning  
The higher education world is changing, and opportunities created by technology coupled with the possibilities of distance education are exciting and intimidating at the same time.  ...  Working together to exercise leadership in discussing, planning and implementing the required changes while, at the same time, focusing on the central importance of students and content delivery, will  ...  Therefore, one has to have Face in order to build one's own network. Normally, a teacher is regarded as one who holds higher social position and has greater Face.  ... 
doi:10.19173/irrodl.v3i2.1084 fatcat:owv5yxnmdjbsncj4hjuv4s73bm

The State of AI Ethics Report (June 2020) [article]

Abhishek Gupta
2020 arXiv   pre-print
These past few months have been especially challenging, and the deployment of technology in ways hitherto untested at an unrivalled pace has left the internet and technology watchers aghast.  ...  It has never been more important that we keep a sharp eye out on the development of this field and how it is shaping our society and interactions with each other.  ...  on a predefined distance metric.  ... 
arXiv:2006.14662v1 fatcat:q76dnqzh4ja5pofurjmpmyeyey

2. Global Problems, Complexity, and Civil Society in East Asia [chapter]

Peter Hayes, Richard Tanter
2015 Complexity, Security and Civil Society in East Asia  
One then uses computer models to allow the agents to interact based on rules of environmental perception, recognition, decision-making, and learning over time. 87 Based on multiple -sometimes thousands  ...  globally while acting locally, but also to cross-country, long-distance, and high-tech imports of renewable energy.  ... 
doi:10.11647/obp.0059.02 fatcat:qruzjhgpbvdlllck2zvjtn3fyq

Purpose, processes, partnerships, and products: four Ps to advance participatory socio-environmental modeling

Steven Gray, Alexey Voinov, Michael Paolisso, Rebecca Jordan, Todd BenDor, Pierre Bommel, Pierre Glynn, Beatrice Hedelin, Klaus Hubacek, Josh Introne, Nagesh Kolagani, Bethany Laursen (+5 others)
2017 Ecological Applications  
However, recent advances in the theory of social-ecological networks and in multi-level network analysis have led to an increase in the study of governance as interconnected social and ecological systems  ...  in research on governance networks.  ...  Our framework is based on an understanding that this food security needs to be based not only on resilient foodscapes, but also foodscapes that are productive, sustainable, and equitable.  ... 
doi:10.1002/eap.1627 pmid:28922513 fatcat:lh6mglx47bbqbh7lsnwiw2jelq

Daily Life in the Land of Bambuk: An Archaeological Study of Political Economy at Diouboye, Senegal

Cameron D. Gokee
2013 Azania  
Lastly, I thank Cameron Gokee for initiating this fruitful collaboration on the archaeology of Diouboye and both Cameron Gokee and Dr.  ...  Additional funds to visit comparative collections housed at the Smithsonian Institution were provided by an NSF Doctoral Dissertation Grant to Cameron Gokee (University of Michigan).  ...  Lattice (CrT) roulettes comprise a network of deep squares or lozenges made by a tool etched with cross-hatching.  ... 
doi:10.1080/0067270x.2013.833723 fatcat:rulqjvyopfhenb2smw4vvfdc6y

WILDS: A Benchmark of in-the-Wild Distribution Shifts [article]

Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, Tony Lee, Etienne David (+11 others)
2021 arXiv   pre-print
To facilitate method development, we provide an open-source package that automates dataset loading, contains default model architectures and hyperparameters, and standardizes evaluations.  ...  On each dataset, we show that standard training yields substantially lower out-of-distribution than in-distribution performance.  ...  Acknowledgements Many people generously volunteered their time and expertise to advise us on Wilds.  ... 
arXiv:2012.07421v3 fatcat:bsohmukpszajxeadeo25oxmbs4

OSI 2017 Summary Report

Glenn Hampson
2017 Open Scholarship Initiative Proceedings  
Most participants see eye to eye on the broad outlines of this challenge, and their reports—considered together and building upon each other—point to specific solutions that can be developed starting this  ...  Fully pursuing all the recommendations will require much more funding, but our hope is that we can get started now on a tight budget and build from there.On behalf of SCI and OSI, thank you to our sponsors  ...  Step 1: Study and map the current IR network. Identify the nodes, as the potential networks and sub-networks. 2.  ... 
doi:10.13021/g8osi.2.2017.1941 fatcat:jmfcqirbgjdihi4dbmqkivrd24

Knowledge sharing for development [chapter]

2012 Development Centre Studies  
and ideas from outside their network borders, which are often quite rigid.  ...  Key Words: knowledge management for development; civil society partnerships and policy dialogues; information and communications technologies for development; online networks; knowledge networks; community  ...  networks by forging new relationships based on reciprocity and trust.  ... 
doi:10.1787/9789264173897-9-en fatcat:q5ifbfw7dfco3eyiywuqbkfdsm
« Previous Showing results 1 — 15 out of 181 results