000			04641nam a22005655i 4500
001			978-981-15-8884-6
003			DE-He213
005			20240423125152.0
007			cr nn 008mamaa
008			201113s2020 si | s |||| 0|eng d
020			_a9789811588846 _9978-981-15-8884-6
024	7		_a10.1007/978-981-15-8884-6 _2doi
050		4	_aQ325.5-.7
072		7	_aUYQM _2bicssc
072		7	_aMAT029000 _2bisacsh
072		7	_aUYQM _2thema
082	0	4	_a006.31 _223
100	1		_aQin, Tao. _eauthor. _4aut _4http://id.loc.gov/vocabulary/relators/aut
245	1	0	_aDual Learning _h[electronic resource] / _cby Tao Qin.
250			_a1st ed. 2020.
264		1	_aSingapore : _bSpringer Nature Singapore : _bImprint: Springer, _c2020.
300			_aXV, 190 p. 52 illus., 24 illus. in color. _bonline resource.
336			_atext _btxt _2rdacontent
337			_acomputer _bc _2rdamedia
338			_aonline resource _bcr _2rdacarrier
347			_atext file _bPDF _2rda
505	0		_aChapter 1. Introduction -- Chapter 2. Machine Learning Basics -- Chapter 3. Deep Learning Basics -- Chapter 4. Dual Learning for Machine Translation and Beyond -- Chapter 5. Dual Learning for Image Translation and Beyond -- Chapter 6. Dual Learning for Speech Processing and Beyond -- Chapter 7. Dual Supervised Learning -- Chapter 8. Dual Inference. Chapter 9. Marginal Probability based Dual Semi-supervised Learning -- Chapter 10. Understanding Dual Reconstruction -- Chapter 11. Connections to Other Learning Paradigms -- Chapter 12. Summary and Outlook.
520			_aMany AI (and machine learning) tasks present in dual forms, e.g., English-to-Chinese translation vs. Chinese-to-English translation, speech recognition vs. speech synthesis,question answering vs. question generation, and image classification vs. image generation. Dual learning is a new learning framework that leverages the primal-dual structure of AI tasks to obtain effective feedback or regularization signals in order to enhance the learning/inference process. Since it was first introduced four years ago, the concept has attracted considerable attention in multiple fields, and been proven effective in numerous applications, such as machine translation, image-to-image translation, speech synthesis and recognition, (visual) question answering and generation, image captioning and generation, and code summarization and generation. Offering a systematic and comprehensive overview of dual learning, this book enables interested researchers (both established and newcomers) and practitioners to gain a better understanding of the state of the art in the field. It also provides suggestions for further reading and tools to help readers advance the area. The book is divided into five parts. The first part gives a brief introduction to machine learning and deep learning. The second part introduces the algorithms based on the dual reconstruction principle using machine translation, image translation, speech processing and other NLP/CV tasks as the demo applications. It covers algorithms, such as dual semi-supervised learning, dual unsupervised learning and multi-agent dual learning. In the context of image translation, it introduces algorithms including CycleGAN, DualGAN, DiscoGAN cdGAN and more recent techniques/applications. The third part presents various work based on the probability principle, including dual supervised learning and dual inference based on the joint-probability principle and dual semi-supervised learning based on the marginal-probability principle. The fourth part reviews various theoretical studies on dual learning and discusses its connections to other learning paradigms. The fifth part provides a summary and suggests future research directions.
650		0	_aMachine learning.
650		0	_aNatural language processing (Computer science).
650		0	_aArtificial intelligence.
650		0	_aComputational linguistics.
650		0	_aComputer vision.
650	1	4	_aMachine Learning.
650	2	4	_aNatural Language Processing (NLP).
650	2	4	_aArtificial Intelligence.
650	2	4	_aComputational Linguistics.
650	2	4	_aComputer Vision.
710	2		_aSpringerLink (Online service)
773	0		_tSpringer Nature eBook
776	0	8	_iPrinted edition: _z9789811588839
776	0	8	_iPrinted edition: _z9789811588853
776	0	8	_iPrinted edition: _z9789811588860
856	4	0	_uhttps://doi.org/10.1007/978-981-15-8884-6
912			_aZDB-2-SCS
912			_aZDB-2-SXCS
942			_cSPRINGER
999			_c175013 _d175013