Fundamentals of deep learning: designing next-generation machine intelligence algorithms
Gespeichert in:
| Beteilige Person: | |
|---|---|
| Weitere beteiligte Personen: | |
| Format: | Buch |
| Sprache: | Englisch |
| Ausgabe: | First edition |
| Schlagwörter: | |
| Links: | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=028713341&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| Beschreibung: | Hier auch später erschienene, unveränderte Nachdrucke |
| Umfang: | xii, 283 Seiten Illustrationen, Diagramme (farbig) |
| ISBN: | 9781491925614 1491925612 9781616895280 |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV043292241 | ||
| 003 | DE-604 | ||
| 005 | 20210105 | ||
| 007 | t| | ||
| 008 | 160119s2017 xx a||| |||| 00||| eng d | ||
| 020 | |a 9781491925614 |c pbk |9 978-1-491-92561-4 | ||
| 020 | |a 1491925612 |c pbk |9 1-491-92561-2 | ||
| 020 | |a 9781616895280 |9 978-1-61689-528-0 | ||
| 035 | |a (OCoLC)1002271546 | ||
| 035 | |a (DE-599)BVBBV043292241 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-739 |a DE-862 |a DE-945 |a DE-1049 |a DE-573 |a DE-11 |a DE-634 |a DE-91G |a DE-M347 |a DE-898 |a DE-83 |a DE-188 | ||
| 084 | |a ST 301 |0 (DE-625)143651: |2 rvk | ||
| 084 | |a ST 300 |0 (DE-625)143650: |2 rvk | ||
| 084 | |a DAT 708f |2 stub | ||
| 084 | |a 68T05 |2 msc | ||
| 100 | 1 | |a Buduma, Nikhil |d 1994- |e Verfasser |0 (DE-588)1136495533 |4 aut | |
| 245 | 1 | 0 | |a Fundamentals of deep learning |b designing next-generation machine intelligence algorithms |c Nikhil Buduma, with contributions by Nicholas Locascio |
| 250 | |a First edition | ||
| 264 | 0 | |a Beijing ; Boston ; Farnham ; Sebastopol ; Tokyo |b O'Reilly |c [June 2017] | |
| 300 | |a xii, 283 Seiten |b Illustrationen, Diagramme (farbig) | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 500 | |a Hier auch später erschienene, unveränderte Nachdrucke | ||
| 650 | 0 | 7 | |a Deep Learning |0 (DE-588)1135597375 |2 gnd |9 rswk-swf |
| 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 | 1 | |a Deep Learning |0 (DE-588)1135597375 |D s |
| 689 | 0 | |5 DE-604 | |
| 700 | 1 | |a Locascio, Nicholas |0 (DE-588)1138387258 |4 ctb | |
| 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=028713341&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-028713341 | |
Datensatz im Suchindex
| DE-BY-TUM_call_number | 0303 DAT 708f 2017 L 749 |
|---|---|
| DE-BY-TUM_katkey | 2288949 |
| DE-BY-TUM_location | 03 |
| DE-BY-TUM_media_number | 040008158661 040008158649 040008162929 040008138258 040008138269 040008138270 040008138281 040008138247 040008138236 040008138225 040008138190 040008138203 040008138214 040008158581 040008158592 040008158616 040008158605 040008158650 040008158672 040008158638 040008158570 040008158627 |
| _version_ | 1823989072169795585 |
| adam_text |
Table ofContents
Preface. ix
1. The Neural Network. 1
Building Intelligent Machines 1
The Limits of Traditional Computer Programs 2
The Mechanics of Machine Learning 3
The Neuron 7
Expressing Linear Perceptrons as Neurons 8
Feed-Forward Neural Networks 9
Linear Neurons and Their Limitations 12
Sigmoid, Tanh, and ReLU Neurons 13
Softmax Output Layers 15
Looking Forward 15
2. Training Feed-Forward Neural Networks. 17
The Fast-Food Problem 17
Gradient Descent 19
The Delta Rule and Learning Rates 21
Gradient Descent with Sigmoidal Neurons 22
The Backpropagation Algorithm 23
Stochastic and Minibatch Gradient Descent 25
Test Sets, Validation Sets, and Overfitting 27
Preventing Overfitting in Deep Neural Networks 34
Summary 37
3. Implementing Neural Networks in TensorFlow. 39
What Is TensorFlow? 39
How Does TensorFlow Compare to Alternatives? 40
iii
Installing TensorFlow 41
Creating and Manipulating TensorFlow Variables 43
TensorFlow Operations 45
Placeholder Tensors 45
Sessions in TensorFlow 46
Navigating Variable Scopes and Sharing Variables 48
Managing Models over the CPU and GPU 51
Specifying the Logistic Regression Model in TensorFlow 52
Logging and Training the Logistic Regression Model 55
Leveraging TensorBoard to Visualize Computation Graphs and Learning 58
Building a Multilayer Model for MNIST in TensorFlow 59
Summary 62
4. Beyond Gradient Descent.63
The Challenges with Gradient Descent 63
Local Minima in the Error Surfaces of Deep Networks 64
Model Identifiability 65
How Pesky Are Spurious Local Minima in Deep Networks? 66
Flat Regions in the Error Surface 69
When the Gradient Points in the Wrong Direction 71
Momentum-Based Optimization 74
A Brief View of Second-Order Methods 77
Learning Rate Adaptation 78
AdaGrad—Accumulating Historical Gradients 79
RMSProp—Exponentially Weighted Moving Average of Gradients 80
Adam—Combining Momentum and RMSProp 81
The Philosophy Behind Optimizer Selection 83
Summary 83
5. Convolutional Neural Networks. 85
Neurons in Human Vision 85
The Shortcomings of Feature Selection 86
Vanilla Deep Neural Networks Dont Scale 89
Filters and Feature Maps 90
Full Description of the Convolutional Layer 95
Max Pooling 98
Full Architectural Description of Convolution Networks 99
Closing the Loop on MNIST with Convolutional Networks 101
Image Preprocessing Pipelines Enable More Robust Models 103
Accelerating Training with Batch Normalization 104
Building a Convolutional Network for CIFAR-10 107
Visualizing Learning in Convolutional Networks 109
iv ՝֊ I Table of Contents
Leveraging Convolutional Filters to Replicate Artistic Styles 113
Learning Convolutional Filters for Other Problem Domains 114
Summary 115
6. Embedding and Representation Learning. 117
Learning Lower-Dimensional Representations 117
Principal Component Analysis 118
Motivating the Autoencoder Architecture 120
Implementing an Autoencoder in TensorFlow 121
Denoising to Force Robust Representations 134
Sparsity in Autoencoders 137
When Context Is More Informative than the Input Vector 140
The Word2Vec Framework 143
Implementing the Skip-Gram Architecture 146
Summary 152
7. ModelsforSequenceAnalysis. 153
Analyzing Variable-Length Inputs 153
Tackling seq2seq with Neural N-Grams 155
Implementing a Part-of֊Speech Tagger 156
Dependency Parsing and SyntaxNet 164
Beam Search and Global Normalization 168
A Case for Stateful Deep Learning Models 172
Recurrent Neural Networks 173
The Challenges with Vanishing Gradients 176
Long Short-Term Memory (LSTM) Units 178
TensorFlow Primitives for RNN Models 183
Implementing a Sentiment Analysis Model 185
Solving seq2seq Tasks with Recurrent Neural Networks 189
Augmenting Recurrent Networks with Attention 191
Dissecting a Neural Translation Network 194
Summary 217
8. Memory Augmented Neural Networks. 219
Neural Turing Machines 219
Attention-Based Memory Access 221
NTM Memory Addressing Mechanisms 223
Differentiable Neural Computers . 226
Interference-Free Writing in DNCs 229
DNC Memory Reuse 230
Temporal Linking of DNC Writes 231
Understanding the DNC Read Head 232
Table of Contents | v
The DNC Controller Network 232
Visualizing the DNC in Action 234
Implementing the DNC in TensorFlow 237
Teaching a DNC to Read and Comprehend 242
Summary 244
9. Deep Reinforcement Learning. 245
Deep Reinforcement Learning Masters Atari Games 245
What Is Reinforcement Learning? 247
Markov Decision Processes (MDP) 248
Policy 249
Future Return 250
Discounted Future Return 251
Explore Versus Exploit 251
Policy Versus Value Learning 253
Policy Learning via Policy Gradients 254
Pole-Cart with Policy Gradients 254
OpenAI Gym 254
Creating an Agent 255
Building the Model and Optimizer 257
Sampling Actions 257
Keeping Track of History 257
Policy Gradient Main Function 258
PGAgent Performance on Pole-Cart 260
Q-Learning and Deep Q-Networks 261
The Bellman Equation 261
Issues with Value Iteration 262
Approximating the Q-Function 262
Deep Q-Network (DQN) 263
Training DQN 263
Learning Stability 263
Target Q-Network 264
Experience Replay 264
From Q-Function to Policy 264
DQN and the Markov Assumption 265
DQN s Solution to the Markov Assumption 265
Playing Breakout wth DQN 265
Building Our Architecture 268
Stacking Frames 268
Setting Up Training Operations 268
Updating Our Target Q-Network 269
Implementing Experience Replay 269
vi | Table of Contents
DQN Main Loop 270
DQNAgent Results on Breakout 272
Improving and Moving Beyond DQN 273
Deep Recurrent Q-Networks (DRQN) 273
Asynchronous Advantage Actor-Critic Agent (A3C) 274
UNsupervised REinforcement and Auxiliary Leaiming (UNREAL) 275
Summary 276
Index. 277
Table of Contents | vii |
| any_adam_object | 1 |
| author | Buduma, Nikhil 1994- |
| author2 | Locascio, Nicholas |
| author2_role | ctb |
| author2_variant | n l nl |
| author_GND | (DE-588)1136495533 (DE-588)1138387258 |
| author_facet | Buduma, Nikhil 1994- Locascio, Nicholas |
| author_role | aut |
| author_sort | Buduma, Nikhil 1994- |
| author_variant | n b nb |
| building | Verbundindex |
| bvnumber | BV043292241 |
| classification_rvk | ST 301 ST 300 |
| classification_tum | DAT 708f |
| ctrlnum | (OCoLC)1002271546 (DE-599)BVBBV043292241 |
| discipline | Informatik |
| edition | First edition |
| 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">BV043292241</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20210105</controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">160119s2017 xx a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781491925614</subfield><subfield code="c">pbk</subfield><subfield code="9">978-1-491-92561-4</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">1491925612</subfield><subfield code="c">pbk</subfield><subfield code="9">1-491-92561-2</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781616895280</subfield><subfield code="9">978-1-61689-528-0</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1002271546</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV043292241</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-739</subfield><subfield code="a">DE-862</subfield><subfield code="a">DE-945</subfield><subfield code="a">DE-1049</subfield><subfield code="a">DE-573</subfield><subfield code="a">DE-11</subfield><subfield code="a">DE-634</subfield><subfield code="a">DE-91G</subfield><subfield code="a">DE-M347</subfield><subfield code="a">DE-898</subfield><subfield code="a">DE-83</subfield><subfield code="a">DE-188</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 301</subfield><subfield code="0">(DE-625)143651:</subfield><subfield code="2">rvk</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">DAT 708f</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">68T05</subfield><subfield code="2">msc</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Buduma, Nikhil</subfield><subfield code="d">1994-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1136495533</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Fundamentals of deep learning</subfield><subfield code="b">designing next-generation machine intelligence algorithms</subfield><subfield code="c">Nikhil Buduma, with contributions by Nicholas Locascio</subfield></datafield><datafield tag="250" ind1=" " ind2=" "><subfield code="a">First edition</subfield></datafield><datafield tag="264" ind1=" " ind2="0"><subfield code="a">Beijing ; Boston ; Farnham ; Sebastopol ; Tokyo</subfield><subfield code="b">O'Reilly</subfield><subfield code="c">[June 2017]</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xii, 283 Seiten</subfield><subfield code="b">Illustrationen, Diagramme (farbig)</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">Hier auch später erschienene, unveränderte Nachdrucke</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Deep Learning</subfield><subfield code="0">(DE-588)1135597375</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="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">Deep Learning</subfield><subfield code="0">(DE-588)1135597375</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Locascio, Nicholas</subfield><subfield code="0">(DE-588)1138387258</subfield><subfield code="4">ctb</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=028713341&sequence=000002&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:BVB01-028713341</subfield></datafield></record></collection> |
| id | DE-604.BV043292241 |
| illustrated | Illustrated |
| indexdate | 2025-02-13T07:00:21Z |
| institution | BVB |
| isbn | 9781491925614 1491925612 9781616895280 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-028713341 |
| oclc_num | 1002271546 |
| open_access_boolean | |
| owner | DE-739 DE-862 DE-BY-FWS DE-945 DE-1049 DE-573 DE-11 DE-634 DE-91G DE-BY-TUM DE-M347 DE-898 DE-BY-UBR DE-83 DE-188 |
| owner_facet | DE-739 DE-862 DE-BY-FWS DE-945 DE-1049 DE-573 DE-11 DE-634 DE-91G DE-BY-TUM DE-M347 DE-898 DE-BY-UBR DE-83 DE-188 |
| physical | xii, 283 Seiten Illustrationen, Diagramme (farbig) |
| publishDateSearch | 2017 |
| publishDateSort | 2017 |
| record_format | marc |
| spellingShingle | Buduma, Nikhil 1994- Fundamentals of deep learning designing next-generation machine intelligence algorithms Deep Learning (DE-588)1135597375 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| subject_GND | (DE-588)1135597375 (DE-588)4193754-5 |
| title | Fundamentals of deep learning designing next-generation machine intelligence algorithms |
| title_auth | Fundamentals of deep learning designing next-generation machine intelligence algorithms |
| title_exact_search | Fundamentals of deep learning designing next-generation machine intelligence algorithms |
| title_full | Fundamentals of deep learning designing next-generation machine intelligence algorithms Nikhil Buduma, with contributions by Nicholas Locascio |
| title_fullStr | Fundamentals of deep learning designing next-generation machine intelligence algorithms Nikhil Buduma, with contributions by Nicholas Locascio |
| title_full_unstemmed | Fundamentals of deep learning designing next-generation machine intelligence algorithms Nikhil Buduma, with contributions by Nicholas Locascio |
| title_short | Fundamentals of deep learning |
| title_sort | fundamentals of deep learning designing next generation machine intelligence algorithms |
| title_sub | designing next-generation machine intelligence algorithms |
| topic | Deep Learning (DE-588)1135597375 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| topic_facet | Deep Learning Maschinelles Lernen |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=028713341&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT budumanikhil fundamentalsofdeeplearningdesigningnextgenerationmachineintelligencealgorithms AT locascionicholas fundamentalsofdeeplearningdesigningnextgenerationmachineintelligencealgorithms |
Inhaltsverzeichnis
Paper/Kapitel scannen lassen
Paper/Kapitel scannen lassen
Teilbibliothek Chemie, Lehrbuchsammlung
| Signatur: |
0303 DAT 708f 2017 L 749 Lageplan |
|---|---|
| Exemplar 1 | Ausleihbar Am Standort |
| Exemplar 2 | Ausleihbar Am Standort |
| Exemplar 3 | Ausleihbar Am Standort |
| Exemplar 4 | Ausleihbar Am Standort |
| Exemplar 5 | Ausleihbar Am Standort |
| Exemplar 6 | Ausleihbar Am Standort |
| Exemplar 7 | Ausleihbar Am Standort |
| Exemplar 8 | Ausleihbar Am Standort |
| Exemplar 9 | Ausleihbar Am Standort |
| Exemplar 10 | Ausleihbar Am Standort |
| Exemplar 11 | Ausleihbar Am Standort |
| Exemplar 12 | Ausleihbar Am Standort |
| Exemplar 13 | Ausleihbar Am Standort |
| Exemplar 14 | Ausleihbar Am Standort |
| Exemplar 15 | Ausleihbar Am Standort |
| Exemplar 16 | Ausleihbar Am Standort |
| Exemplar 17 | Ausleihbar Am Standort |
| Exemplar 18 | Ausleihbar Am Standort |
| Exemplar 19 | Ausleihbar Am Standort |
| Exemplar 20 | Ausleihbar Am Standort |
| Exemplar 21 | Ausleihbar Am Standort |
| Exemplar 22 | Ausleihbar Ausgeliehen – Rückgabe bis: 25.03.2025 |