Python deep learning: next generation techniques to revolutionize computer vision, AI, speech and data analysis
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Birmingham ; Mumbai
Packt>
April 2017
|
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis |
| Beschreibung: | xii, 383 Seiten Illustrationen, Diagramme |
| ISBN: | 9781786464453 |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV044886097 | ||
| 003 | DE-604 | ||
| 005 | 20180704 | ||
| 007 | t | ||
| 008 | 180328s2017 a||| |||| 00||| eng d | ||
| 020 | |a 9781786464453 |c pbk |9 978-1-78646-445-3 | ||
| 035 | |a (OCoLC)988378485 | ||
| 035 | |a (DE-599)BVBBV044886097 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-29T |a DE-703 |a DE-739 | ||
| 084 | |a ST 300 |0 (DE-625)143650: |2 rvk | ||
| 084 | |a ST 302 |0 (DE-625)143652: |2 rvk | ||
| 100 | 1 | |a Zocca, Valentino |e Verfasser |0 (DE-588)1136427856 |4 aut | |
| 245 | 1 | 0 | |a Python deep learning |b next generation techniques to revolutionize computer vision, AI, speech and data analysis |c Valentino Zocca, Gianmario Spacagna, Daniel Slater, Peter Roelants |
| 264 | 1 | |a Birmingham ; Mumbai |b Packt> |c April 2017 | |
| 300 | |a xii, 383 Seiten |b Illustrationen, Diagramme | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 650 | 4 | |a Python (Computer program language) | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Neural networks (Computer science) | |
| 650 | 7 | |a Machine learning |2 fast | |
| 650 | 7 | |a Neural networks (Computer science) |2 fast | |
| 650 | 7 | |a Python (Computer program language) |2 fast | |
| 650 | 0 | 7 | |a Python |g Programmiersprache |0 (DE-588)4434275-5 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Lernendes System |0 (DE-588)4120666-6 |2 gnd |9 rswk-swf |
| 689 | 0 | 0 | |a Lernendes System |0 (DE-588)4120666-6 |D s |
| 689 | 0 | 1 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 0 | 2 | |a Python |g Programmiersprache |0 (DE-588)4434275-5 |D s |
| 689 | 0 | |5 DE-604 | |
| 700 | 1 | |a Spacagna, Gianmario |e Verfasser |0 (DE-588)1136428097 |4 aut | |
| 700 | 1 | |a Slater, Daniel |e Verfasser |0 (DE-588)1136428313 |4 aut | |
| 700 | 1 | |a Roelants, Peter |e Verfasser |0 (DE-588)1136428461 |4 aut | |
| 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=030280202&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-030280202 | ||
Datensatz im Suchindex
| _version_ | 1804178428410200064 |
|---|---|
| adam_text | Table of Contents
Preface____________________________________________________________________vii
Chapter 1: Machine Learning - An Introduction________________________________1
What is machine learning? 2
Different machine learning approaches 3
Supervised learning 3
Unsupervised learning 6
Reinforcement learning 8
Steps Involved in machine learning systems 9
Brief description of popular techniques/algorithms 13
Linear regression 14
Decision trees 16
K-means 17
Naive Bayes 19
Support vector machines 20
The cross-entropy method 22
Neural networks 23
Deep learning 25
Applications in real life 26
A popular open source package 28
Summary 35
Chapter 2: Neural Networks__________________________________________________37
Why neural networks? 38
Fundamentals 39
Neurons and layers 40
Different types of activation function 46
The back-propagation algorithm 51
Linear regression 51
Logistic regression 53
Back-propagation 56
Applications in industry 60
Signal processing 60
Medical 60
Autonomous car driving 61
Business 61
Pattern recognition 61
Speech production 61
Code example of a neural network for the function xor 62
Summary 68
Chapter 3: Deep Learning Fundamentals____________________________________69
What is deep learning? 70
Fundamental concepts 72
Feature learning 73
Deep learning algorithms 83
Deep learning applications 84
Speech recognition 84
Object recognition and classification 86
GPU versus CPU 89
Popular open source libraries - an introduction 91
Theano 91
TensorFlow 92
Keras 92
Sample deep neural net code using Keras 93
Summary 98
Chapter 4: Unsupervised Feature Learning_______________________________ 101
Autoencoders 104
Network design 108
Regularization techniques for autoencoders 111
Denoising autoencoders 111
Contractive autoencoders 112
Sparse autoencoders 114
Summary of autoencoders 116
Restricted Boltzmann machines 117
Hopfield networks and Boltzmann machines 120
Boltzmann machine 123
Restricted Boltzmann machine 126
Implementation in TensorFlow 128
Deep belief networks 133
Summary 134
Chapter 5: Image Recognition____________________________________________ 137
Similarities between artificial and biological models 138
Intuition and justification 139
Convolutional layers 141
Stride and padding in convolutional layers 148
Pooling layers 150
Dropout 152
Convolutional layers in deep learning 152
Convolutional layers in Theano 154
A convolutional layer example with Keras to recognize digits 156
A convolutional layer example with Keras for cifarlO 159
Pre-training 161
Summary 163
Chapter 6: Recurrent Neural Networks and Language Models 165
Recurrent neural networks 166
RNN — how to implement and train 168
Backpropagation through time 169
Vanishing and exploding gradients 172
Long short term memory 175
Language modeling 178
Word-based models 178
N-grams 179
Neural language models 180
Character-based model 185
Preprocessing and reading data 186
LSTM network 187
Training 189
Sampling 191
Example training 192
Speech recognition 193
Speech recognition pipeline 193
Speech as input data 195
Preprocessing 195
Acoustic model 197
Deep belief networks 197
Recurrent neural networks 198
CTC 198
Attention-based models 199
Decoding 199
End-to-end models 200
Summary 201
Bibliography 201
Chapter 7: Deep Learning for Board Games 207
Early game playing Al 209
Using the min-max algorithm to value game states 210
Implementing a Python Tic-Tac-Toe game 213
Learning a value function 223
Training Al to master Go 224
Upper confidence bounds applied to trees 227
Deep learning in Monte Carlo Tree Search 236
Quick recap on reinforcement learning 238
Policy gradients for learning policy functions 238
Policy gradients in AlphaGo 247
Summary 249
Chapter 8: Deep Learning for Computer Games_________________________251
A supervised learning approach to games 251
Applying genetic algorithms to playing games 253
Q-Learning 254
Q-fu notion 256
Q-learning in action 257
Dynamic games 263
Experience replay 268
Epsilon greedy 271
Atari Breakout 272
Atari Breakout random benchmark 273
Preprocessing the screen 275
Creating a deep convolutional network 278
Convergence issues in Q-learning 283
Policy gradients versus Q-learning 285
Actor-critic methods 285
Baseline for variance reduction 287
Generalized advantage estimator 287
Asynchronous methods 288
Model-based approaches 289
Summary 292
Chapter 9: Anomaly Detection_______________________________________293
What is anomaly and outlier detection? 294
Real-world applications of anomaly detection 297
Popular shallow machine learning techniques 298
Data modeling 299
Detection modeling 299
Anomaly detection using deep auto-encoders 301
H20
Getting started with H20 303
Examples 305
MNIST digit anomaly recognition 305
Electrocardiogram pulse detection 306
Summary 316
Chapter 10: Building a Production-ready Intrusion 321
Detection System 323
What is a data product? 324
Training 326
Weights initialization 326
Parallel SGD using HOGWILD! 328
Adaptive learning 330
Rate annealing 331
Momentum 331
Nesterov s acceleration 332
Newton s method 333
Adagrad 334
Adadelta 335
Distributed learning via Map/Reduce 337
Sparkling Water 341
Testing 344
Model validation 351
Labeled Data 353
Unlabeled Data 356
Summary of validation 359
Hyper-parameters tuning 360
End-to-end evaluation 364
A/B Testing 366
A summary of testing 369
Deployment 370
POJO model export 370
Anomaly score APIs 373
A summary of deployment 376
Summary 377
Index 379
|
| any_adam_object | 1 |
| author | Zocca, Valentino Spacagna, Gianmario Slater, Daniel Roelants, Peter |
| author_GND | (DE-588)1136427856 (DE-588)1136428097 (DE-588)1136428313 (DE-588)1136428461 |
| author_facet | Zocca, Valentino Spacagna, Gianmario Slater, Daniel Roelants, Peter |
| author_role | aut aut aut aut |
| author_sort | Zocca, Valentino |
| author_variant | v z vz g s gs d s ds p r pr |
| building | Verbundindex |
| bvnumber | BV044886097 |
| classification_rvk | ST 300 ST 302 |
| ctrlnum | (OCoLC)988378485 (DE-599)BVBBV044886097 |
| discipline | Informatik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02187nam a2200481 c 4500</leader><controlfield tag="001">BV044886097</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20180704 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">180328s2017 a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781786464453</subfield><subfield code="c">pbk</subfield><subfield code="9">978-1-78646-445-3</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)988378485</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV044886097</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-29T</subfield><subfield code="a">DE-703</subfield><subfield code="a">DE-739</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">Zocca, Valentino</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1136427856</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Python deep learning</subfield><subfield code="b">next generation techniques to revolutionize computer vision, AI, speech and data analysis</subfield><subfield code="c">Valentino Zocca, Gianmario Spacagna, Daniel Slater, Peter Roelants</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Birmingham ; Mumbai</subfield><subfield code="b">Packt></subfield><subfield code="c">April 2017</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xii, 383 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</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=" " ind2="4"><subfield code="a">Python (Computer program language)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Neural networks (Computer science)</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Machine learning</subfield><subfield code="2">fast</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Neural networks (Computer science)</subfield><subfield code="2">fast</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Python (Computer program language)</subfield><subfield code="2">fast</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Python</subfield><subfield code="g">Programmiersprache</subfield><subfield code="0">(DE-588)4434275-5</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="650" ind1="0" ind2="7"><subfield code="a">Lernendes System</subfield><subfield code="0">(DE-588)4120666-6</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Lernendes System</subfield><subfield code="0">(DE-588)4120666-6</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><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="2"><subfield code="a">Python</subfield><subfield code="g">Programmiersprache</subfield><subfield code="0">(DE-588)4434275-5</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">Spacagna, Gianmario</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1136428097</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Slater, Daniel</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1136428313</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Roelants, Peter</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1136428461</subfield><subfield code="4">aut</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=030280202&sequence=000001&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:BVB01-030280202</subfield></datafield></record></collection> |
| id | DE-604.BV044886097 |
| illustrated | Illustrated |
| indexdate | 2024-07-10T08:03:49Z |
| institution | BVB |
| isbn | 9781786464453 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-030280202 |
| oclc_num | 988378485 |
| open_access_boolean | |
| owner | DE-29T DE-703 DE-739 |
| owner_facet | DE-29T DE-703 DE-739 |
| physical | xii, 383 Seiten Illustrationen, Diagramme |
| publishDate | 2017 |
| publishDateSearch | 2017 |
| publishDateSort | 2017 |
| publisher | Packt> |
| record_format | marc |
| spelling | Zocca, Valentino Verfasser (DE-588)1136427856 aut Python deep learning next generation techniques to revolutionize computer vision, AI, speech and data analysis Valentino Zocca, Gianmario Spacagna, Daniel Slater, Peter Roelants Birmingham ; Mumbai Packt> April 2017 xii, 383 Seiten Illustrationen, Diagramme txt rdacontent n rdamedia nc rdacarrier Python (Computer program language) Machine learning Neural networks (Computer science) Machine learning fast Neural networks (Computer science) fast Python (Computer program language) fast Python Programmiersprache (DE-588)4434275-5 gnd rswk-swf Maschinelles Lernen (DE-588)4193754-5 gnd rswk-swf Lernendes System (DE-588)4120666-6 gnd rswk-swf Lernendes System (DE-588)4120666-6 s Maschinelles Lernen (DE-588)4193754-5 s Python Programmiersprache (DE-588)4434275-5 s DE-604 Spacagna, Gianmario Verfasser (DE-588)1136428097 aut Slater, Daniel Verfasser (DE-588)1136428313 aut Roelants, Peter Verfasser (DE-588)1136428461 aut Digitalisierung UB Passau - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=030280202&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Zocca, Valentino Spacagna, Gianmario Slater, Daniel Roelants, Peter Python deep learning next generation techniques to revolutionize computer vision, AI, speech and data analysis Python (Computer program language) Machine learning Neural networks (Computer science) Machine learning fast Neural networks (Computer science) fast Python (Computer program language) fast Python Programmiersprache (DE-588)4434275-5 gnd Maschinelles Lernen (DE-588)4193754-5 gnd Lernendes System (DE-588)4120666-6 gnd |
| subject_GND | (DE-588)4434275-5 (DE-588)4193754-5 (DE-588)4120666-6 |
| title | Python deep learning next generation techniques to revolutionize computer vision, AI, speech and data analysis |
| title_auth | Python deep learning next generation techniques to revolutionize computer vision, AI, speech and data analysis |
| title_exact_search | Python deep learning next generation techniques to revolutionize computer vision, AI, speech and data analysis |
| title_full | Python deep learning next generation techniques to revolutionize computer vision, AI, speech and data analysis Valentino Zocca, Gianmario Spacagna, Daniel Slater, Peter Roelants |
| title_fullStr | Python deep learning next generation techniques to revolutionize computer vision, AI, speech and data analysis Valentino Zocca, Gianmario Spacagna, Daniel Slater, Peter Roelants |
| title_full_unstemmed | Python deep learning next generation techniques to revolutionize computer vision, AI, speech and data analysis Valentino Zocca, Gianmario Spacagna, Daniel Slater, Peter Roelants |
| title_short | Python deep learning |
| title_sort | python deep learning next generation techniques to revolutionize computer vision ai speech and data analysis |
| title_sub | next generation techniques to revolutionize computer vision, AI, speech and data analysis |
| topic | Python (Computer program language) Machine learning Neural networks (Computer science) Machine learning fast Neural networks (Computer science) fast Python (Computer program language) fast Python Programmiersprache (DE-588)4434275-5 gnd Maschinelles Lernen (DE-588)4193754-5 gnd Lernendes System (DE-588)4120666-6 gnd |
| topic_facet | Python (Computer program language) Machine learning Neural networks (Computer science) Python Programmiersprache Maschinelles Lernen Lernendes System |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=030280202&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT zoccavalentino pythondeeplearningnextgenerationtechniquestorevolutionizecomputervisionaispeechanddataanalysis AT spacagnagianmario pythondeeplearningnextgenerationtechniquestorevolutionizecomputervisionaispeechanddataanalysis AT slaterdaniel pythondeeplearningnextgenerationtechniquestorevolutionizecomputervisionaispeechanddataanalysis AT roelantspeter pythondeeplearningnextgenerationtechniquestorevolutionizecomputervisionaispeechanddataanalysis |