000 03759nam a22005895i 4500
001 978-3-319-55312-2
003 DE-He213
005 20220801221600.0
007 cr nn 008mamaa
008 170330s2017 sz | s |||| 0|eng d
020 _a9783319553122
_9978-3-319-55312-2
024 7 _a10.1007/978-3-319-55312-2
_2doi
050 4 _aQ342
072 7 _aUYQ
_2bicssc
072 7 _aTEC009000
_2bisacsh
072 7 _aUYQ
_2thema
082 0 4 _a006.3
_223
100 1 _aKulkarni, Parag.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_956842
245 1 0 _aReverse Hypothesis Machine Learning
_h[electronic resource] :
_bA Practitioner's Perspective /
_cby Parag Kulkarni.
250 _a1st ed. 2017.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2017.
300 _aXVI, 138 p. 61 illus., 9 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aIntelligent Systems Reference Library,
_x1868-4408 ;
_v128
505 0 _aPattern Apart -- Understanding Machine Learning Opportunities -- Systemic Machine Learning -- Reinforcement and Deep Reinforcement Machine Learning -- Creative Machine Learning -- Co-operative and Collective learning for Creative Machine Learning -- Building Creative Machines with Optimal Machine Learning and Creative Machine Learning Applications -- Conclusion – Learning Continues.
520 _aThis book introduces a paradigm of reverse hypothesis machines (RHM), focusing on knowledge innovation and machine learning. Knowledge- acquisition -based learning is constrained by large volumes of data and is time consuming. Hence Knowledge innovation based learning is the need of time. Since under-learning results in cognitive inabilities and over-learning compromises freedom, there is need for optimal machine learning. All existing learning techniques rely on mapping input and output and establishing mathematical relationships between them. Though methods change the paradigm remains the same—the forward hypothesis machine paradigm, which tries to minimize uncertainty. The RHM, on the other hand, makes use of uncertainty for creative learning. The approach uses limited data to help identify new and surprising solutions. It focuses on improving learnability, unlike traditional approaches, which focus on accuracy. The book is useful as a reference book for machine learning researchers and professionals as well as machine intelligence enthusiasts. It can also used by practitioners to develop new machine learning applications to solve problems that require creativity.
650 0 _aComputational intelligence.
_97716
650 0 _aKnowledge management.
_912739
650 0 _aMachinery.
_931894
650 0 _aTechnological innovations.
_97308
650 0 _aElectronics.
_93425
650 1 4 _aComputational Intelligence.
_97716
650 2 4 _aKnowledge Management.
_912739
650 2 4 _aMachinery and Machine Elements.
_931895
650 2 4 _aInnovation and Technology Management.
_933002
650 2 4 _aElectronics and Microelectronics, Instrumentation.
_932249
710 2 _aSpringerLink (Online service)
_956843
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783319553115
776 0 8 _iPrinted edition:
_z9783319553139
776 0 8 _iPrinted edition:
_z9783319856261
830 0 _aIntelligent Systems Reference Library,
_x1868-4408 ;
_v128
_956844
856 4 0 _uhttps://doi.org/10.1007/978-3-319-55312-2
912 _aZDB-2-ENG
912 _aZDB-2-SXE
942 _cEBK
999 _c79825
_d79825