Machine learning: a constraint-based approach
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Amsterdam
Elsevier, MK, Morgan Kaufmann Publishers
[2018]
|
| Subjects: | |
| Online Access: | Inhaltsverzeichnis |
| Physical Description: | XX, 560 Seiten Illustrationen |
| ISBN: | 9780081006597 |
Staff View
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV044658065 | ||
| 003 | DE-604 | ||
| 005 | 20181024 | ||
| 007 | t | ||
| 008 | 171130s2018 a||| |||| 00||| eng d | ||
| 020 | |a 9780081006597 |c pbk |9 978-0-08-100659-7 | ||
| 035 | |a (OCoLC)1013733692 | ||
| 035 | |a (DE-599)BVBBV044658065 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-1050 |a DE-11 |a DE-898 |a DE-20 |a DE-573 |a DE-29T |a DE-739 |a DE-863 |a DE-634 | ||
| 084 | |a ST 300 |0 (DE-625)143650: |2 rvk | ||
| 084 | |a ST 302 |0 (DE-625)143652: |2 rvk | ||
| 100 | 1 | |a Gori, Marco |e Verfasser |0 (DE-588)1145940498 |4 aut | |
| 245 | 1 | 0 | |a Machine learning |b a constraint-based approach |c Marco Gori, Università di Siena |
| 264 | 1 | |a Amsterdam |b Elsevier, MK, Morgan Kaufmann Publishers |c [2018] | |
| 300 | |a XX, 560 Seiten |b Illustrationen | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 689 | 0 | 0 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 0 | |5 DE-604 | |
| 856 | 4 | 2 | |m Digitalisierung UB Passau - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=030055638&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-030055638 | ||
Record in the Search Index
| DE-BY-863_location | 1000 |
|---|---|
| DE-BY-FWS_call_number | 1000/ST 302 G669 |
| DE-BY-FWS_katkey | 700975 |
| DE-BY-FWS_media_number | 083101413046 |
| _version_ | 1824553544425930752 |
| adam_text | Contents
Preface................................................................. xiii
Notes on the Exercises................................................... xix
CHAPTER 1 The Big Picture.................................................. 2
1.1 Why Do Machines Need to Learn?.......................... 3
1.1.1 Learning Tasks...................................... 4
1.1.2 Symbolic and Subsymbolic Representations of the
Environment.......................................... 9
1.1.3 Biological and Artificial Neural Networks........... 11
1.1.4 Protocols of Learning............................... 13
1.1.5 Constraint-Based Learning........................... 19
1.2 Principles and Practice................................... 28
1.2.1 The Puzzling Nature of Induction.................... 28
1.2.2 Learning Principles................................. 34
1.2.3 The Role of Time in Learning Processes ............. 34
1.2.4 Focus of Attention.................................. 35
1.3 Hands-on Experience...................................... 38
1.3.1 Measuring the Success of Experiments................ 39
1.3.2 Handwritten Character Recognition .................. 40
1.3.3 Setting up a Machine Learning Experiment............ 42
1.3.4 Test and Experimental Remarks....................... 45
1.4 Challenges in Machine Learning........................... 50
1.4.1 Learning to See..................................... 50
1.4.2 Speech Understanding ............................... 51
1.4.3 Agents Living in Their Own Environment.............. 52
1.5 Scholia.................................................. 54
CHAPTER 2 Learning Principles............................................. 60
2.1 Environmental Constraints................................ 61
2.1.1 Loss and Risk Functions............................. 61
2.1.2 Ill-Position of Constraint-Induced Risk Functions. 69
2.1.3 Risk Minimization................................... 71
2.1.4 The Bias-Variance Dilemma........................... 75
2.2 Statistical Learning..................................... 83
2.2.1 Maximum Likelihood Estimation....................... 83
2.2.2 Bayesian Inference.................................. 86
2.2.3 Bayesian Learning................................. 88
2.2.4 Graphical Modes..................................... 89
2.2.5 Frequentist and Bayesian Approach................... 92
2.3 Information-Based Learning............................. 95
2.3.1 A Motivating Example................................ 95
* ■
VII
Contents
2.3.2 Principle of Maximum Entropy.......................... 97
2.3.3 Maximum Mutual Information ........................... 99
2.4 Learning Under the Parsimony Principle................... 104
2.4.1 The Parsimony Principle.............................. 104
2.4.2 Minimum Description Length........................... 104
2.4.3 MDL and Regularization............................... 110
2.4.4 Statistical Interpretation of Regularization......... 113
2.5 Scholia................................................... 115
CHAPTER 3 Linear Threshold Machines............................... 122
3.1 Linear Machines........................................... 123
3.1.1 Normal Equations..................................... 128
3.1.2 Undetermined Problems and Pseudoinversion........... 129
3.1.3 Ridge Regression..................................... 132
3.1.4 Primal and Dual Representations...................... 134
3.2 Linear Machines With Threshold Units ..................... 141
3.2.1 Predicate-Order and Representational Issues.......... 142
3.2.2 Optimality for Linearly-Separable Examples........... 149
3.2.3 Failing to Separate.................................. 151
3.3 Statistical View......................................... 155
3.3.1 Bayesian Decision and Linear Discrimination......... 155
3.3.2 Logistic Regression.................................. 156
3.3.3 The Parsimony Principle Meets the Bayesian Decision 158
3.3.4 LMS in the Statistical Framework..................... 159
3.4 Algorithmic Issues ....................................... 162
3.4.1 Gradient Descent..................................... 162
3.4.2 Stochastic Gradient Descent.......................... 164
3.4.3 The Perceptron Algorithm............................. 165
3.4.4 Complexity Issues.................................... 169
3.5 Scholia................................................... 175
CHAPTER 4 Kernel Machines.................................................. 186
4.1 Feature Space............................................. 187
4.1.1 Polynomial Preprocessing ............................ 187
4.1.2 Boolean Enrichment................................... 188
4.1.3 Invariant Feature Maps............................... 189
4.1.4 Linear-Separability in High-Dimensional Spaces...... 190
4.2 Maximum Margin Problem.................................... 194
4.2.1 Classification Under Linear-Separability............. 194
4.2.2 Dealing With Soft-Constraints........................ 198
4.2.3 Regression........................................... 201
4.3 Kernel Functions.......................................... 207
4.3.1 Similarity and Kernel Trick.......................... 207
4.3.2 Characterization of Kernels.......................... 208
Contents ix
4.3.3 The Reproducing Kernel Map.......................... 212
4.3.4 Types of Kernels.................................... 214
4.4 Regularization........................................... 220
4.4.1 Regularized Risks................................... 220
4.4.2 Regularization in RKHS.............................. 222
4.4.3 Minimization of Regularized Risks................... 223
4.4.4 Regularization Operators............................ 224
4.5 Scholia.................................................. 230
CHAPTER 5 Deep Architectures............................................. 236
5.1 Architectural Issues...................................... 237
5.1.1 Digraphs and Feedforward Networks................... 238
5.1.2 Deep Paths.......................................... 240
5.1.3 From Deep to Relaxation-Based Architectures....... 243
5.1.4 Classifiers, Regressors, and Auto-Encoders.......... 244
5.2 Realization of Boolean Functions....................... 247
5.2.1 Canonical Realizations by and-or Gates.............. 247
5.2.2 Universal nand Realization.......................... 251
5.2.3 Shallow vs Deep Realizations........................ 251
5.2.4 LTU-Based Realizations and Complexity Issues...... 254
5.3 Realization of Real-Valued Functions..................... 265
5.3.1 Computational Geometry-Based Realizations......... 265
5.3.2 Universal Approximation............................. 268
5.3.3 Solution Space and Separation Surfaces.............. 271
5.3.4 Deep Networks and Representational Issues........... 276
5.4 Convolutional Networks................................... 280
5.4.1 Kernels, Convolutions, and Receptive Fields......... 280
5.4.2 Incorporating Invariance............................ 288
5.4.3 Deep Convolutional Networks......................... 293
5.5 Learning in Feedforward Networks......................... 298
5.5.1 Supervised Learning................................. 298
5.5.2 Backpropagation..................................... 298
5.5.3 Symbolic and Automatic Differentiation ............. 306
5.5.4 Regularization Issues .............................. 308
5.6 Complexity Issues........................................ 313
5.6.1 On the Problem of Local Minima...................... 313
5.6.2 Facing Saturation................................... 319
5.6.3 Complexity and Numerical Issues..................... 323
5.7 Scholia.................................................. 326
CHAPTER 6 Learning and Reasoning With Constraints...................... 340
6.1 Constraint Machines....................................... 343
6.1.1 Walking Through Learning and Inference ............. 343
6.1.2 A Unified View of Constrained Environments........ 352
Contents
6.1.3 Functional Representation of Learning Tasks......... 359
6.1.4 Reasoning With Constraints.......................... 364
6.2 Logic Constraints in the Environment.................... 373
6.2.1 Formal Logic and Complexity of Reasoning............ 373
6.2.2 Environments With Symbols and Subsymbols........... 376
6.2.3 T-Norms............................................. 384
6.2.4 Lukasiewicz Propositional Logic..................... 388
6.3 Diffusion Machines....................................... 392
6.3.1 Data Models......................................... 393
6.3.2 Diffusion in Spatiotemporal Environments............ 399
6.3.3 Recurrent Neural Networks........................... 400
6.4 Algorithmic Issues ...................................... 404
6.4.1 Pointwise Content-Based Constraints................. 405
6.4.2 Propositional Constraints in the Input Space........ 408
6.4.3 Supervised Learning With Linear Constraints........ 413
6.4.4 Learning Under Diffusion Constraints ............... 416
6.5 Life-Long Learning Agents................................ 424
6.5.1 Cognitive Action and Temporal Manifolds............. 425
6.5.2 Energy Balance...................................... 430
6.5.3 Focus of Attention, Teaching, and Active Learning__ 431
6.5.4 Developmental Learning.............................. 433
6.6 Scholia.................................................. 437
CHAPTER 7 Epilogue....................................................... 446
CHAPTER 8 Answers to Exercises........................................... 452
Section 1.1............................................... 453
Section 1.2............................................... 454
Section 1.3............................................... 455
Section 2.1............................................... 455
Section 2.2............................................... 459
Section3.1................................................ 465
Section 3.2............................................... 468
Section 3.3............................................... 471
Section 3.4............................................... 472
Section 4.1............................................... 473
Section 4.2............................................... 475
Section 4.3............................................... 479
Section 4.4............................................... 486
Section 5.1............................................... 487
Section 5.2............................................... 489
Section 5.3............................................... 490
Section 5.4............................................... 492
Section 5.5............................................... 494
Contents xi
Section 5.7............................................. 495
Section 6.1............................................. 497
Section 6.2............................................. 500
Section 6.3............................................. 502
Section 6.4............................................. 504
Appendix A Constrained Optimization in Finite Dimensions............. 508
Appendix B Regularization Operators................................... 512
Appendix C Calculus of Variations..................................... 518
C.1 Functionals and Variations............................. 518
C.2 Basic Notion on Variations............................. 520
C.3 Euler-Lagrange Equations............................... 523
C.4 Variational Problems With Subsidiary Conditions........ 526
Appendix D Index to Notation.......................................... 530
Bibliography.......................................................... 534
Index................................................................. 552
|
| any_adam_object | 1 |
| author | Gori, Marco |
| author_GND | (DE-588)1145940498 |
| author_facet | Gori, Marco |
| author_role | aut |
| author_sort | Gori, Marco |
| author_variant | m g mg |
| building | Verbundindex |
| bvnumber | BV044658065 |
| classification_rvk | ST 300 ST 302 |
| ctrlnum | (OCoLC)1013733692 (DE-599)BVBBV044658065 |
| discipline | Informatik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01379nam a2200325 c 4500</leader><controlfield tag="001">BV044658065</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20181024 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">171130s2018 a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780081006597</subfield><subfield code="c">pbk</subfield><subfield code="9">978-0-08-100659-7</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1013733692</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV044658065</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-1050</subfield><subfield code="a">DE-11</subfield><subfield code="a">DE-898</subfield><subfield code="a">DE-20</subfield><subfield code="a">DE-573</subfield><subfield code="a">DE-29T</subfield><subfield code="a">DE-739</subfield><subfield code="a">DE-863</subfield><subfield code="a">DE-634</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 300</subfield><subfield code="0">(DE-625)143650:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 302</subfield><subfield code="0">(DE-625)143652:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Gori, Marco</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1145940498</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Machine learning</subfield><subfield code="b">a constraint-based approach</subfield><subfield code="c">Marco Gori, Università di Siena</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Amsterdam</subfield><subfield code="b">Elsevier, MK, Morgan Kaufmann Publishers</subfield><subfield code="c">[2018]</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">XX, 560 Seiten</subfield><subfield code="b">Illustrationen</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Passau - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=030055638&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-030055638</subfield></datafield></record></collection> |
| id | DE-604.BV044658065 |
| illustrated | Illustrated |
| indexdate | 2025-02-20T06:37:34Z |
| institution | BVB |
| isbn | 9780081006597 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-030055638 |
| oclc_num | 1013733692 |
| open_access_boolean | |
| owner | DE-1050 DE-11 DE-898 DE-BY-UBR DE-20 DE-573 DE-29T DE-739 DE-863 DE-BY-FWS DE-634 |
| owner_facet | DE-1050 DE-11 DE-898 DE-BY-UBR DE-20 DE-573 DE-29T DE-739 DE-863 DE-BY-FWS DE-634 |
| physical | XX, 560 Seiten Illustrationen |
| publishDate | 2018 |
| publishDateSearch | 2018 |
| publishDateSort | 2018 |
| publisher | Elsevier, MK, Morgan Kaufmann Publishers |
| record_format | marc |
| spellingShingle | Gori, Marco Machine learning a constraint-based approach Maschinelles Lernen (DE-588)4193754-5 gnd |
| subject_GND | (DE-588)4193754-5 |
| title | Machine learning a constraint-based approach |
| title_auth | Machine learning a constraint-based approach |
| title_exact_search | Machine learning a constraint-based approach |
| title_full | Machine learning a constraint-based approach Marco Gori, Università di Siena |
| title_fullStr | Machine learning a constraint-based approach Marco Gori, Università di Siena |
| title_full_unstemmed | Machine learning a constraint-based approach Marco Gori, Università di Siena |
| title_short | Machine learning |
| title_sort | machine learning a constraint based approach |
| title_sub | a constraint-based approach |
| topic | Maschinelles Lernen (DE-588)4193754-5 gnd |
| topic_facet | Maschinelles Lernen |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=030055638&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT gorimarco machinelearningaconstraintbasedapproach |
Indexes
THWS Würzburg Zentralbibliothek Lesesaal
| Call Number: |
1000 ST 302 G669 |
|---|---|
| Copy 1 | ausleihbar Available Place a Hold |