Explanation based neural network learning a lifelong learning approach:
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | German |
| Veröffentlicht: |
1995
|
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis |
| Beschreibung: | Bonn, Univ., Diss., 1995 (Nicht für den Austausch) |
| Beschreibung: | X, 222 S. Ill., graph. Darst. |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV010662095 | ||
| 003 | DE-604 | ||
| 005 | 19960603 | ||
| 007 | t | ||
| 008 | 960227s1995 gw ad|| m||| 00||| ger d | ||
| 016 | 7 | |a 946531382 |2 DE-101 | |
| 035 | |a (OCoLC)258277960 | ||
| 035 | |a (DE-599)BVBBV010662095 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a ger | |
| 044 | |a gw |c DE | ||
| 049 | |a DE-91 | ||
| 084 | |a ST 300 |0 (DE-625)143650: |2 rvk | ||
| 084 | |a ST 304 |0 (DE-625)143653: |2 rvk | ||
| 084 | |a DAT 717d |2 stub | ||
| 084 | |a DAT 708d |2 stub | ||
| 100 | 1 | |a Thrun, Sebastian |d 1967- |e Verfasser |0 (DE-588)112396682 |4 aut | |
| 245 | 1 | 0 | |a Explanation based neural network learning a lifelong learning approach |c vorgelegt von Sebastian Thrun |
| 246 | 1 | 3 | |a Explanation-based neural network learning a lifelong learning approach |
| 264 | 1 | |c 1995 | |
| 300 | |a X, 222 S. |b Ill., graph. Darst. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 500 | |a Bonn, Univ., Diss., 1995 (Nicht für den Austausch) | ||
| 650 | 0 | 7 | |a Erklärungskomponente |0 (DE-588)4267341-0 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Neuronales Netz |0 (DE-588)4226127-2 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Lebenslanges Lernen |0 (DE-588)4134373-6 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 689 | 0 | 0 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 0 | 1 | |a Lebenslanges Lernen |0 (DE-588)4134373-6 |D s |
| 689 | 0 | 2 | |a Neuronales Netz |0 (DE-588)4226127-2 |D s |
| 689 | 0 | 3 | |a Erklärungskomponente |0 (DE-588)4267341-0 |D s |
| 689 | 0 | |5 DE-604 | |
| 856 | 4 | 2 | |m DNB Datenaustausch |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=007117009&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-007117009 | |
Datensatz im Suchindex
| _version_ | 1812453632525729792 |
|---|---|
| adam_text |
CONTENTS
1 INTRODUCTION 1
1.1 MOTIVATION. 1
1.2 LIFELONG LEARNING. 3
1.2.1 BIAS. 3
1.2.2 LEARNING BIAS-THE META-LEVEL LEARNING PROBLEM. 5
1.2.3 A SIMPLE COMPLEXITY CONSIDERATION . 7
1.3 THE EBNN APPROACH TO LIFELONG LEARNING. 10
1.3.1 LEARNING DOMAIN KNOWLEDGE. 10
1.3.2 BIAS IN EBNN.
12
1.3.3 THE THESIS. 13
1.4 OVERVIEW. 13
2 EXPLANATION-BASED NEURAL NETWORK LEARNING 15
2.1 INDUCTIVE NEURAL NETWORK LEARNING. 17
2.1.1 INDUCTIVE LEARNING. ^
2.1.2 ARTIFICIAL NEURAL NETWORKS. 1 ^
2.1.3 FUNCTION APPROXIMATION. 19
BIBLIOGRAFISCHE INFORMATIONEN
HTTP://D-NB.INFO/946531382
IV _
CONTENTS
2.1.4 PARAMETER SEARCH . 21
2.1.5 APPLICATION DOMAINS. 22
2.2 ANALYTICAL LEARNING. 23
2.3 WHY INTEGRATE INDUCTION AND ANALYSIS?. 26
2.4 THE EBNN LEARNING ALGORITHM. 27
2.4.1 INTEGRATING INDUCTION AND ANALYSIS . 28
2.4.2 ACCOMMODATING IMPERFECT DOMAIN KNOWLEDGE. 31
2.5 A SIMPLE EXAMPLE. 34
2.6 THE RELATION OF NEURAL AND SYMBOLIC EXPLANATION-BASED LEARNING. 36
2.7 OTHER APPROACHES THAT COMBINE INDUCTION AND ANALYSIS . 38
2.8 EBNN AND LIFELONG LEARNING. 40
3 THE INVARIANCE APPROACH 43
3.1 INTRODUCTION. 43
3.2 LIFELONG SUPERVISED LEARNING. 44
3.2.1 SUPERVISED LEARNING. 44
3.2.2 LEARNING MANY RELATED FUNCTIONS. 45
3.2.3 LEARNING AT THE META-LEVEL. 46
3.3 THE INVARIANCE APPROACH . 48
3.3.1 INVARIANCE MAPPINGS. 49
3.3.2 LEARNING THE INVARIANTS . 50
3.3.3 APPLYING EBNN. 51
3.4 EXAMPLE: LEARNING TO RECOGNIZE OBJECTS. 53
3.4.1 DOMAIN DESCRIPTION. 53
CONTENTS
_V
3.4.2 TRAINING THE INVARIANCE NETWORK. 55
3.4.3 LEARNING TO RECOGNIZE SHOES. 57
3.4.4 THE ROLE OF THE INVARIANCE NETWORK. 61
3.4.5 APPLYING EBNN SELECTIVELY. 63
3.5 ALTERNATIVE METHODS. 65
3.5.1 USING THE DOMAIN THEORY FOR CLASSIFICATION. 66
3.5.2 LEARNING WITH HINTS. 69
3.5.3 MEMORY-BASED METHODS. 71
3.5.4 LEARNING REPRESENTATIONS. 72
3.5.5 COMPARISON. 75
3.6 REMARKS. 25
4 REINFORCEMENT LEARNING 81
4.1 LEARNING CONTROL. 82
4.2 LIFELONG CONTROL LEARNING. 86
4.3 Q-LEARNING . 89
4.3.1 THE Q-LEARNING RULE. 89
4.3.2 TEMPORAL DIFFERENCE LEARNING. 91
4.3.3 APPLYING EBNN. 92
4.3.4 LOB* IN Q-LEARNING. 95
4.3.5 DOMAIN THEORY. 96
4.4 GENERALIZING FUNCTION APPROXIMATORS AND Q-LEARNING. 97
4.4.1 THEORETICAL RESULTS . 97
4.4.2 THE OVERESTIMATION PHENOMENON
99
VI_CONTENTS
4.4.3 BOUNDS FOR EXPECTED FAILURE OF Q-LEARNING.101
4.4.4 EMPIRICAL RESULTS.104
4.4.5 INTERPRETATION OF THE RESULTS.108
4.5 REMARKS.110
5 EMPIRICAL RESULTS 115
5.1 LEARNING ROBOT CONTROL.116
5.2 NAVIGATION.117
5.2.1 EXPERIMENTAL SETUP.117
5.2.2 EXPERIMENTAL RESULTS .119
5.3 SIMULATION RESULTS.123
5.4 APPROACHING AND GRASPING A CUP.128
5.4.1 LEARNING TASK.128
5.4.2 EXPERIMENTAL RESULTS .130
5.5 NEUROCHESS.133
5.5.1 LEARNING IN CHESS.133
5.5.2 TEMPORAL DIFFERENCE LEARNING IN CHESS.134
5.5.3 APPLYING EBNN.136
5.5.4 SOFTWARE ARCHITECTURE.139
5.5.5 TRAINING ISSUES.143
5.5.6 RESULTS.148
5.5.7 EVALUATION.151
5.6 REMARKS.154
CONTENTS
_VII
6 DISCUSSION 157
6.1 SUMMARY.157
6.1.1 SUMMARY OF EBNN.157
6.1.2 MAIN EXPERIMENTAL RESULTS.160
6.1.3 CONTRIBUTIONS.160
6.2 OPEN PROBLEMS.161
6.3 RELATED WORK .165
6.4 CONCLUDING REMARKS.171
APPENDIX A: AN ALGORITHM FOR FITTING VALUES AND SLOPES WITH ARTIFICIAL
NEURAL NETWORKS 173
A.L DEFINITIONS.174
A.2 NETWORK FORWARD PROPAGATION.174
A.3 FORWARD PROPAGATION OF AUXILIARY GRADIENTS.175
A.4 ERROR FUNCTIONS .176
A.5 MINIMIZING THE VALUE ERROR.176
A.6 MINIMIZING THE SLOPE ERROR.177
A.L
THE SQUASHING FUNCTION A AND ITS DERIVATIVES.178
A.8 UPDATING THE NETWORK WEIGHTS AND BIASES.179
APPENDIX B: PROOFS OF THE THEOREMS 181
APPENDIX C: EXAMPLE CHESS GAMES 185
C.L GAME 1.185
C.2 GAME 2.192
BIBLIOGRAPHY
197
VIII
CONTENTS
INDEX
217
CURRICULUM VITAE
223 |
| any_adam_object | 1 |
| author | Thrun, Sebastian 1967- |
| author_GND | (DE-588)112396682 |
| author_facet | Thrun, Sebastian 1967- |
| author_role | aut |
| author_sort | Thrun, Sebastian 1967- |
| author_variant | s t st |
| building | Verbundindex |
| bvnumber | BV010662095 |
| classification_rvk | ST 300 ST 304 |
| classification_tum | DAT 717d DAT 708d |
| ctrlnum | (OCoLC)258277960 (DE-599)BVBBV010662095 |
| discipline | Informatik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>00000nam a2200000 c 4500</leader><controlfield tag="001">BV010662095</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">19960603</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">960227s1995 gw ad|| m||| 00||| ger d</controlfield><datafield tag="016" ind1="7" ind2=" "><subfield code="a">946531382</subfield><subfield code="2">DE-101</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)258277960</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV010662095</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">ger</subfield></datafield><datafield tag="044" ind1=" " ind2=" "><subfield code="a">gw</subfield><subfield code="c">DE</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91</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 304</subfield><subfield code="0">(DE-625)143653:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 717d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 708d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Thrun, Sebastian</subfield><subfield code="d">1967-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)112396682</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Explanation based neural network learning a lifelong learning approach</subfield><subfield code="c">vorgelegt von Sebastian Thrun</subfield></datafield><datafield tag="246" ind1="1" ind2="3"><subfield code="a">Explanation-based neural network learning a lifelong learning approach</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">1995</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">X, 222 S.</subfield><subfield code="b">Ill., graph. Darst.</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="500" ind1=" " ind2=" "><subfield code="a">Bonn, Univ., Diss., 1995 (Nicht für den Austausch)</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Erklärungskomponente</subfield><subfield code="0">(DE-588)4267341-0</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Neuronales Netz</subfield><subfield code="0">(DE-588)4226127-2</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Lebenslanges Lernen</subfield><subfield code="0">(DE-588)4134373-6</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</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="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</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="1"><subfield code="a">Lebenslanges Lernen</subfield><subfield code="0">(DE-588)4134373-6</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">Neuronales Netz</subfield><subfield code="0">(DE-588)4226127-2</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="3"><subfield code="a">Erklärungskomponente</subfield><subfield code="0">(DE-588)4267341-0</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">DNB Datenaustausch</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=007117009&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-007117009</subfield></datafield></record></collection> |
| genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV010662095 |
| illustrated | Illustrated |
| indexdate | 2024-10-09T16:14:38Z |
| institution | BVB |
| language | German |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-007117009 |
| oclc_num | 258277960 |
| open_access_boolean | |
| owner | DE-91 DE-BY-TUM |
| owner_facet | DE-91 DE-BY-TUM |
| physical | X, 222 S. Ill., graph. Darst. |
| publishDate | 1995 |
| publishDateSearch | 1995 |
| publishDateSort | 1995 |
| record_format | marc |
| spelling | Thrun, Sebastian 1967- Verfasser (DE-588)112396682 aut Explanation based neural network learning a lifelong learning approach vorgelegt von Sebastian Thrun Explanation-based neural network learning a lifelong learning approach 1995 X, 222 S. Ill., graph. Darst. txt rdacontent n rdamedia nc rdacarrier Bonn, Univ., Diss., 1995 (Nicht für den Austausch) Erklärungskomponente (DE-588)4267341-0 gnd rswk-swf Neuronales Netz (DE-588)4226127-2 gnd rswk-swf Lebenslanges Lernen (DE-588)4134373-6 gnd rswk-swf Maschinelles Lernen (DE-588)4193754-5 gnd rswk-swf (DE-588)4113937-9 Hochschulschrift gnd-content Maschinelles Lernen (DE-588)4193754-5 s Lebenslanges Lernen (DE-588)4134373-6 s Neuronales Netz (DE-588)4226127-2 s Erklärungskomponente (DE-588)4267341-0 s DE-604 DNB Datenaustausch application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=007117009&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Thrun, Sebastian 1967- Explanation based neural network learning a lifelong learning approach Erklärungskomponente (DE-588)4267341-0 gnd Neuronales Netz (DE-588)4226127-2 gnd Lebenslanges Lernen (DE-588)4134373-6 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| subject_GND | (DE-588)4267341-0 (DE-588)4226127-2 (DE-588)4134373-6 (DE-588)4193754-5 (DE-588)4113937-9 |
| title | Explanation based neural network learning a lifelong learning approach |
| title_alt | Explanation-based neural network learning a lifelong learning approach |
| title_auth | Explanation based neural network learning a lifelong learning approach |
| title_exact_search | Explanation based neural network learning a lifelong learning approach |
| title_full | Explanation based neural network learning a lifelong learning approach vorgelegt von Sebastian Thrun |
| title_fullStr | Explanation based neural network learning a lifelong learning approach vorgelegt von Sebastian Thrun |
| title_full_unstemmed | Explanation based neural network learning a lifelong learning approach vorgelegt von Sebastian Thrun |
| title_short | Explanation based neural network learning a lifelong learning approach |
| title_sort | explanation based neural network learning a lifelong learning approach |
| topic | Erklärungskomponente (DE-588)4267341-0 gnd Neuronales Netz (DE-588)4226127-2 gnd Lebenslanges Lernen (DE-588)4134373-6 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| topic_facet | Erklärungskomponente Neuronales Netz Lebenslanges Lernen Maschinelles Lernen Hochschulschrift |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=007117009&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT thrunsebastian explanationbasedneuralnetworklearningalifelonglearningapproach |