Filters








82,329 Hits in 9.7 sec

Online Non-Additive Path Learning under Full and Partial Information [article]

Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Holakou Rahmanian, Manfred K. Warmuth
2019 arXiv   pre-print
We present new online algorithms for path learning with non-additive count-based gains for the three settings of full information, semi-bandit and full bandit with very favorable regret guarantees.  ...  We study the problem of online path learning with non-additive gains, which is a central problem appearing in several applications, including ensemble structured prediction.  ...  Acknowledgments The work of MM was partly funded by NSF CCF-1535987 and NSF IIS-1618662. Part of this work was done while MKW was at UC Santa Cruz, supported by NSF grant IIS-1619271.  ... 
arXiv:1804.06518v4 fatcat:sf4in3czibauzaksyvgy2a6jka

PeerLens

Meng Xia, Mingfei Sun, Huan Wei, Qing Chen, Yong Wang, Lei Shi, Huamin Qu, Xiaojuan Ma
2019 Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems - CHI '19  
If it is the author's pre-published version, changes introduced as a result of publishing processes such as copy-editing and formatting may not be reflected in this document.  ...  ACKNOWLEDGEMENTS This work is partially sponsored by Innovation and Technology Fund (ITF) with No. ITS/388/17FP and Lei Shi is supported by NSFC Grant with No. 61772504.  ...  We also thank Hangzhou Dianzi University Online Judge for providing the data.  ... 
doi:10.1145/3290605.3300864 dblp:conf/chi/XiaSWCWSQM19 fatcat:3o7l6wbsgzfvfppxqdisxhdxxi

Meta-path based multi-network collective link prediction

Jiawei Zhang, Philip S. Yu, Zhi-Hua Zhou
2014 Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '14  
To utilize useful connection information, a subset of the most informative "social meta paths" are picked, the process of which is formally defined as "social meta path selection" in this paper.  ...  Built with heterogenous topological features extracted based on the selected "social meta paths" in the multiple partially aligned social networks, Mli can help refine and disambiguate the prediction results  ...  2 → D 2 → D 1 , we can go from non-anchor user C 1 to anchor user D 1 , which is an instance of Ψ2(U 1 , U 1 ); in addition, by following path C 1 → A 1 → A 2 → B 2 → B 1 → E 1 , we can go from non-anchor  ... 
doi:10.1145/2623330.2623645 dblp:conf/kdd/ZhangYZ14 fatcat:ofawls7p4jhhpgbqjwf46lj4si

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  and automatic data clustering by t-distributed stochastic neighbour embedding; adaptive learning rate clipping to stabilize learning; generative adversarial networks for compressed sensing with spiral  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4598227 fatcat:hm2ksetmsvf37adjjefmmbakvq

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  and automatic data clustering by t-distributed stochastic neighbour embedding; adaptive learning rate clipping to stabilize learning; generative adversarial networks for compressed sensing with spiral  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4591029 fatcat:zn2hvfyupvdwlnvsscdgswayci

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  and automatic data clustering by t-distributed stochastic neighbour embedding; adaptive learning rate clipping to stabilize learning; generative adversarial networks for compressed sensing with spiral  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4399748 fatcat:63ggmnviczg6vlnqugbnrexsgy

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  and automatic data clustering by t-distributed stochastic neighbour embedding; adaptive learning rate clipping to stabilize learning; generative adversarial networks for compressed sensing with spiral  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4415407 fatcat:6dejwzzpmfegnfuktrld6zgpiq

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  and automatic data clustering by t-distributed stochastic neighbour embedding; adaptive learning rate clipping to stabilize learning; generative adversarial networks for compressed sensing with spiral  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4413249 fatcat:35qbhenysfhvza2roihx52afuy

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  and automatic data clustering by t-distributed stochastic neighbour embedding; adaptive learning rate clipping to stabilize learning; generative adversarial networks for compressed sensing with spiral  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4429792 fatcat:qs6yuapx4vdbdmwna7ix7nnwty

Cooperative Multi-Agent Reinforcement Learning with Approximate Model Learning

Young Joon Park, Young Jae Lee, Seoung Bum Kim
2020 IEEE Access  
To address issues with partial observability and unstable learning, we propose using auxiliary prediction networks to approximate state transitions and the reward function.  ...  The actor networks cause the agents to communicate using forward and backward paths and to determine subsequent actions.  ...  This model can address the challenge of non-Markovian and nonstationary environments during learning [15] and can access the additional state information of other agents while promoting communication  ... 
doi:10.1109/access.2020.3007219 fatcat:j2u2j7zb4zgbboip25eqys34xa

PILOT

Stina Bridgeman, Michael T. Goodrich, Stephen G. Kobourov, Roberto Tamassia
2000 Proceedings of the thirty-first SIGCSE technical symposium on Computer science education - SIGCSE '00  
, its automated grading mechanism, and its ability to award partial credit to proposed solutions.  ...  The strengths of PILOT are its universal access and platform independence, its use as an algorithm visualization tool, its ability to test algorithmic concepts, its support for graph generation and layout  ...  In addition, online grading also provides fast and consistent grading, provably correct solutions, and pointers to information relevant to the question.  ... 
doi:10.1145/330908.331843 dblp:conf/sigcse/BridgemanGKT00 fatcat:enxlm7sei5bpleomoc33oq7usm

PILOT

Stina Bridgeman, Michael T. Goodrich, Stephen G. Kobourov, Roberto Tamassia
2000 ACM SIGCSE Bulletin  
, its automated grading mechanism, and its ability to award partial credit to proposed solutions.  ...  The strengths of PILOT are its universal access and platform independence, its use as an algorithm visualization tool, its ability to test algorithmic concepts, its support for graph generation and layout  ...  In addition, online grading also provides fast and consistent grading, provably correct solutions, and pointers to information relevant to the question.  ... 
doi:10.1145/331795.331843 fatcat:glshdz3lxbbgfp7j54homjdecm

Adaptive Information Gathering via Imitation Learning

Sanjiban Choudhury, Ashish Kapoor, Gireeja Ranade, Sebastian Scherer, Debadeepta Dey
2017 Robotics: Science and Systems XIII  
The policy imitates a clairvoyant oracle -an oracle that at train time has full knowledge about the world map and can compute maximally informative sensing locations.  ...  We present a novel data-driven imitation learning framework to efficiently train information gathering policies.  ...  ACKNOWLEDGEMENT The authors thank Sankalp Arora for insightful discussions and open source code for exploration in MATLAB.  ... 
doi:10.15607/rss.2017.xiii.041 dblp:conf/rss/ChoudhuryKRSD17 fatcat:j32lcxikcfffbfnccvcm5z3s3a

Towards Practical PPM Spam Filtering: Experiments for the TREC 2006 Spam Track

Andrej Bratko, Bogdan Filipic, Blaz Zupan
2006 Text Retrieval Conference  
A very simple strategy of training on most recent examples was used for the active learning task, and found to work surprisingly well given its simplicity.  ...  We submitted a single filter for the evaluation, based on the Prediction by Partial Matching compression scheme, a method that performed well in the previous TREC evaluation.  ...  The area under the ROC curve (%) is plotted as a function of the number of training messages for the "most recent first" active learning strategy, and random sampling with an equal number of training examples  ... 
dblp:conf/trec/BratkoFZ06 fatcat:ycdkaxro3jbinlt5vnmcuxu4xq

The Optimal Path of College Art Teaching Based on Embedded Sensor Network

Yumei Li, Jiang Zhu, Rashid A Saeed
2022 Wireless Communications and Mobile Computing  
At the same time, the education and teaching methods optimized based on sensor network technology can better play the role of education and teaching so that students' learning enthusiasm has been improved  ...  , and sensor technology, and carrying out experimental research on the application of embedded sensor network in the optimization path of college art teaching.  ...  In addition to the online art course teaching in colleges and universities, the social platform has also launched online art teaching courses for others to learn.  ... 
doi:10.1155/2022/1937259 fatcat:oh2ygy4kyfh7zmk3cy425jwgay
« Previous Showing results 1 — 15 out of 82,329 results