Filters








8 Hits in 7.8 sec

Score-Based Generative Classifiers [article]

Roland S. Zimmermann, Lukas Schott, Yang Song, Benjamin A. Dunn, David A. Klindt
2021 arXiv   pre-print
The tremendous success of generative models in recent years raises the question whether they can also be used to perform classification.  ...  Additionally, on natural image datasets, previous results have suggested a trade-off between the likelihood of the data and classification accuracy.  ...  Roweis, editors, Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, June 5-9, 2008, volume 307 of ACM International Conference Proceeding  ... 
arXiv:2110.00473v2 fatcat:6yer6cgkxnbf7kg2m2xmxjtre4

Unsupervised Text Summarization via Mixed Model Back-Translation [article]

Yacine Jernite
2019 arXiv   pre-print
In this work, we extend the paradigm to the problem of learning a sentence summarization system from unaligned data.  ...  We present several initial models which rely on the asymmetrical nature of the task to perform the first back-translation step, and demonstrate the value of combining the data created by these diverse  ...  In Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, June 5-9, 2008, pages 1096-1103. Yau-Shian Wang and Hung-yi Lee. 2018.  ... 
arXiv:1908.08566v1 fatcat:nx5i2l3bhbhnjb4n3hzp2gzkai

AdapterFusion: Non-Destructive Task Composition for Transfer Learning [article]

Jonas Pfeiffer, Aishwarya Kamath, Andreas Rücklé, Kyunghyun Cho, Iryna Gurevych
2021 arXiv   pre-print
We empirically evaluate AdapterFusion on 16 diverse NLU tasks, and find that it effectively combines various types of knowledge at different layers of the model.  ...  First, in the knowledge extraction stage we learn task specific parameters called adapters, that encapsulate the task-specific information.  ...  This work was partly supported by Samsung Advanced Institute of Technology (Next Generation Deep Learning: from pattern recognition to AI) and Samsung Research (Improving Deep Learning using Latent Structure  ... 
arXiv:2005.00247v3 fatcat:rhjexrlidzcjtck5xjqcmaxmxe

Language Modeling Teaches You More Syntax than Translation Does: Lessons Learned Through Auxiliary Task Analysis [article]

Kelly W. Zhang, Samuel R. Bowman
2019 arXiv   pre-print
We still, though, do not yet have a clear understanding of how the choice of pretraining objective affects the type of linguistic information that models learn.  ...  We make a fair comparison between the tasks by holding constant the quantity and genre of the training data, as well as the LSTM architecture.  ...  We acknowledge the support of NVIDIA Corporation with the donation of the Titan X Pascal GPU used for this research. SB acknowledges support from Google and Samsung Research.  ... 
arXiv:1809.10040v2 fatcat:prdxahnek5dyxnej3kcj2exyii

Learning-induced categorical perception in a neural network model [article]

Christian Thériault, Fernanda Pérez-Gay, Dan Rivas, Stevan Harnad
2018 arXiv   pre-print
There are several hypotheses about the causes of CP (e.g., language, learning, evolution) but no functional model.  ...  In human cognition, the expansion of perceived between-category distances and compression of within-category distances is known as categorical perception (CP).  ...  ., Extracting and composing robust features with denoising autencoders.Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, June 5-9, 2008 Pattern  ... 
arXiv:1805.04567v1 fatcat:yv2pca7uobefnlc6hrhisf2n5e

An Anytime Algorithm for Reachability on Uncountable MDP [article]

Kush Grover, Jan Křetínský, Tobias Meggendorfer, Maximilian Weininger
2020 arXiv   pre-print
Moreover, it simultaneously is the first algorithm able to utilize learning approaches without sacrificing guarantees and it further allows for combination with existing heuristics.  ...  It is the first such anytime algorithm, meaning that at any point in time it can return the current approximation with its precision.  ...  Roweis, editors, Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, June 5-9, 2008, volume 307 of ACM International Conference Proceeding Series  ... 
arXiv:2008.04824v1 fatcat:54e5csqhojhdpc6brhwero4plq

Διερεύνηση της γεωλογικής δομής και της τεκτονικής παραμόρφωσης της Σερβομακεδονικής Μάζας στα όρη των Κερδυλλίων και Βερτίσκου (Βόρεια Ελλάδα)

Αναστάσιος Π. Πλούγαρλης
2020
In particular, the roof of the upper marble horizon of the Kerdyllion Unit does not constitute the criterion for distinguishing the rocks of the two units, as has been established so far, but the extensive  ...  The present thesis aims at the detailed study of the tectonostratigraphy and deforming evolution of this very important area, at the boundary of the units comprising the Serbo-Macedonian Massif.  ...  In Proceedings of the Twenty-Fourth International Conference on Machine Learning, (ICML 2007), volume 227 of ACM International Conference Proceeding Series, pages 641–648, Corvallis, Oregon, USA.  ... 
doi:10.26262/heal.auth.ir.327189 fatcat:snneggenqzdnvbl7kn7zpztqqq

Special Issue: Semantic Informational Technologies

Vladimir Fomichov, Anton Železnikar, Matjaž Gams, Jožef Stefan, Drago Torkar, Jožef Stefan, Editorial Board, Juan Carlos, Augusto, Argentina, Costin Badica, Romania (+20 others)
2010 unpublished
approaches to learning.  ...  Theoretical background for presented system is provided by trialogical learning, an approach in the domain of collaborative learning or working, with several similar aspects to existing constructivist  ...  Acknowledgements The research work presented in this paper is partly supported by grant DO 02-292/December 2008 "Effective search of conceptual information with applications in medical informatics", funded  ... 
fatcat:wragndobczejtfiashj42sdi5q