Applied deep learning: a case-based approach to understanding deep neural networks
Gespeichert in:
1. Verfasser: | |
---|---|
Format: | Buch |
Sprache: | English |
Veröffentlicht: |
New York
Apress
[2018]
|
Schriftenreihe: | For professionals by professionals
|
Schlagworte: | |
Online-Zugang: | Inhaltstext http://www.springer.com/ Inhaltsverzeichnis |
Beschreibung: | Auf der Coverrückseite: Shelve in: Programming languages / Python, user level: Intermediate - advanced |
Beschreibung: | xxi, 410 Seiten Illustrationen, Diagramme 25.4 cm x 17.8 cm |
ISBN: | 9781484237892 1484237897 |
Internformat
MARC
LEADER | 00000nam a2200000 c 4500 | ||
---|---|---|---|
001 | BV045244452 | ||
003 | DE-604 | ||
005 | 20190621 | ||
007 | t| | ||
008 | 181022s2018 xxua||| |||| 00||| eng d | ||
016 | 7 | |a 1159912017 |2 DE-101 | |
020 | |a 9781484237892 |c Festeinband : circa EUR 35.30 (DE) (freier Preis), circa EUR 36.29 (AT) (freier Preis), circa CHF 36.50 (freier Preis) |9 978-1-4842-3789-2 | ||
020 | |a 1484237897 |9 1-4842-3789-7 | ||
024 | 3 | |a 9781484237892 | |
028 | 5 | 2 | |a Bestellnummer: 978-1-4842-3789-2 |
028 | 5 | 2 | |a Bestellnummer: 86959676 |
035 | |a (OCoLC)1060778685 | ||
035 | |a (DE-599)DNB1159912017 | ||
040 | |a DE-604 |b ger |e rda | ||
041 | 0 | |a eng | |
044 | |a xxu |c XD-US | ||
049 | |a DE-29T |a DE-20 |a DE-739 |a DE-11 | ||
084 | |a ST 302 |0 (DE-625)143652: |2 rvk | ||
084 | |a ST 300 |0 (DE-625)143650: |2 rvk | ||
100 | 1 | |a Michelucci, Umberto |e Verfasser |0 (DE-588)1170709281 |4 aut | |
245 | 1 | 0 | |a Applied deep learning |b a case-based approach to understanding deep neural networks |c Umberto Michelucci |
264 | 1 | |a New York |b Apress |c [2018] | |
300 | |a xxi, 410 Seiten |b Illustrationen, Diagramme |c 25.4 cm x 17.8 cm | ||
336 | |b txt |2 rdacontent | ||
337 | |b n |2 rdamedia | ||
338 | |b nc |2 rdacarrier | ||
490 | 0 | |a For professionals by professionals | |
500 | |a Auf der Coverrückseite: Shelve in: Programming languages / Python, user level: Intermediate - advanced | ||
650 | 0 | 7 | |a Deep Learning |0 (DE-588)1135597375 |2 gnd |9 rswk-swf |
653 | |a UMA | ||
653 | |a Convolutional Neural Networks | ||
653 | |a Deep Learning | ||
653 | |a Dropout | ||
653 | |a Neuron Activation Functions | ||
653 | |a Python | ||
653 | |a Recursive Neural Networks | ||
653 | |a Regularization | ||
653 | |a Skilearn | ||
653 | |a TensorFlow | ||
653 | |a UM | ||
653 | |a UN | ||
653 | |a UMA | ||
689 | 0 | 0 | |a Deep Learning |0 (DE-588)1135597375 |D s |
689 | 0 | |5 DE-604 | |
710 | 2 | |a Apress L.P. |0 (DE-588)1065538766 |4 pbl | |
776 | 0 | 8 | |i Erscheint auch als |n Online-Ausgabe |z 978-1-4842-3790-8 |
856 | 4 | 2 | |m X:MVB |q text/html |u http://deposit.dnb.de/cgi-bin/dokserv?id=5dd6ec1196b34c58b7e9d5eae79fa300&prov=M&dok_var=1&dok_ext=htm |3 Inhaltstext |
856 | 4 | 2 | |m X:MVB |u http://www.springer.com/ |
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=030632589&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-030632589 |
Datensatz im Suchindex
_version_ | 1823924576518668288 |
---|---|
adam_text |
Table of Contents About the Author. . . xi About the Technical Reviewer. xiii Acknowledgments. . .xv Introduction. . . . xvii Chapter 1: Computational Graphs and TensorFlow. .1 How to Set Up Your Python Environment. .1 Creating an Environment. . .3 Installing TensorFlow. . . .9 Jupyter Notebooks. 11 Basic Introduction to TensorFlow. 14 Computational Graphs. . . 14 Tensors. . . 17 Creating and Running a Computational Graph. 19 Computational Graph with tf.constant. . 19 Computational Graph with tf.Variable. 20 Computational Graph with tf.placeholder. 22 Differences Between run and eval. . 25 Dependencies Between Nodes. . 26 Tips on How to Create and Close a Session. , 27 Chapter 2: Single
Neuron., 31 The Structure of a Neuron. ,31 Matrix Notation. . . ,35 Python Implementation Tip: Loops and NumPy. ,36 Activation Functions. . . ,38
TABLE OF CONTENTS Cost Function and Gradient Descent: The Quirks of the Learning Rate.47 Learning Rate in a Practical Example. . . 50 Example of Linear Regression in tensorflow. . .57 Example of Logistic Regression. Cost Function. 70 70 Activation Function. The Dataset. tensorflow Implementation.75 References. 80 Chapter 3: Feedforward Neural Networks.83 Network Architecture. 84 Output of Neurons. 87 Summary of Matrix Dimensions. 88 Example: Equations for a Network with Three Layers. . 88 Hyperparameters in Fully Connected Networks. 90 softmax Function for Multiclass
Classification. 90 A Brief Digression: Overfitting. 91 A Practical Example of Overfitting. 92 Basic Error Analysis. . 99 The Zalando Dataset. . Building a Model with tensorflow. 105 Network Architecture. Modifying Labels for the softmax Function—One-Hot Encoding.108 The tensorflow Model. Gradient Descent Variations. . Batch Gradient Descent. 114 Stochastic Gradient Descent. . 116 Mini-Batch Gradient Descent.117 Comparison of the Variations.119 Examples of Wrong
Predictions.123 Weight Initialization.125 VI
TABLE OF CONTENTS Adding Many Layers Efficiently. . . . 127 Advantages of Additional Hidden Layers. . 130 Comparing Different Networks. . 131 Tips for Choosing the Right Network. . 135 Chapter 4: Training Neural Networks. Dynamic Learning Rate Decay. .137 .137 ‘139 Iterations or Epochs?. . . Staircase Decay. . . Step Decay. . . . . . .142 Inverse Time Decay. . .145 Exponential Decay. . 148 Natural Exponential Decay. . .150 tensorflow Implementation. . .158 Applying the Methods to the Zalando Dataset . . .162 Common Optimizers. . . . 140 .163 163 Exponentially Weighted Averages. . Momentum. . .167 RMSProp. . .172 Adam. .
.175 Which Optimizer Should I Use?. 177 Example of Self-Developed Optimizer. . 179 Chapter 5: Regularization. .185 Complex Networks and Overfitting. . . .185 What Is Regularization?. . . .190 About Network Complexity. . .191 EpNorm. . . . 192 £2 Regularization. . . 192 Theory of i2 Regularization. . 192 tensorflow Implementation. . Є, Regularization. . . 194 . 205 VII
TABLE OF CONTENTS Theory of Et Regularization and tensorflow Implementation. 206 Are Weights Really Going to Zero?. . 208 Dropout. . . .211 Early Stopping. . . . 215 Additional Methods. . . 216 Chapter 6: Metric Analysis. 217 Human-Level Performance and Bayes Error.218 A Short Story About Human-Level Performance.221 Human-Level Performance on MNIST. . . .223 Bias. Metric Analysis Diagram. Training Set Overfitting. . 225 Test
Set. How to Split Your Dataset. Unbalanced Class Distribution: What Can Happen. Precision, Recall, and F1 Metrics.239 Datasets with Different Distributions.245 К-Fold Cross-Validation. . Manual Metric Analysis: An Example. Chapter 7: Hyperparameter Tuning. 271 Black-Box Optimization. Notes on Black-Box Functions. 273 The Problem of Hyperparameter Tuning.274 Sample Black-Box Problem. Grid Search. 277 Random Search.
. 282 Coarse-to-Fine Optimization.285 Bayesian Optimization. Nadaraya-Watson Regression. Gaussian Process. 291 viii 271
TABLE OF CONTENTS Stationary Process. . 292 Prediction with Gaussian Processes. Acquisition Function. . . 292 298 Upper Confidence Bound (UCB). . .299 Example. 300 Sampling on a Logarithmic Scale.310 Hyperparameter Tuning with the Zalando Dataset. . 312 A Quick Note on the Radial Basis Function. . . 321 Chapter 8: Convolutional and Recurrent Neural Networks. .323 Kernels and Filters. 323 Convolution.325 Examples of Convolution. 334
Pooling. Padding. Building Blocks of a CNN. . . . 346 Convolutional Layers. 347 Pooling Layers. 34 Stacking Layers Together. 34 Example of a CNN. 350 Introduction to RNNs.355 Notation. 357 Basic Idea of RNNs. 358 Why the Name Recurrent?. 359 Learning to Count.359 Chapter 9: A Research Project. 365 The Problem
Description. 365 The Mathematical Model. . 369 Regression Problem. 369 Dataset Preparation. 375 Model Training. ix
TABLE OF CONTENTS Chapter 10: Logistic Regression from Scratch. .391 Mathematics Behind Logistic Regression. . 392 Python Implementation.395 Test of the Model. 398 Dataset Preparation. 398 Running the Test. 400 Conclusion. Index. . x |
any_adam_object | 1 |
author | Michelucci, Umberto |
author_GND | (DE-588)1170709281 |
author_facet | Michelucci, Umberto |
author_role | aut |
author_sort | Michelucci, Umberto |
author_variant | u m um |
building | Verbundindex |
bvnumber | BV045244452 |
classification_rvk | ST 302 ST 300 |
ctrlnum | (OCoLC)1060778685 (DE-599)DNB1159912017 |
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">BV045244452</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20190621</controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">181022s2018 xxua||| |||| 00||| eng d</controlfield><datafield tag="016" ind1="7" ind2=" "><subfield code="a">1159912017</subfield><subfield code="2">DE-101</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781484237892</subfield><subfield code="c">Festeinband : circa EUR 35.30 (DE) (freier Preis), circa EUR 36.29 (AT) (freier Preis), circa CHF 36.50 (freier Preis)</subfield><subfield code="9">978-1-4842-3789-2</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">1484237897</subfield><subfield code="9">1-4842-3789-7</subfield></datafield><datafield tag="024" ind1="3" ind2=" "><subfield code="a">9781484237892</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">Bestellnummer: 978-1-4842-3789-2</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">Bestellnummer: 86959676</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1060778685</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DNB1159912017</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="044" ind1=" " ind2=" "><subfield code="a">xxu</subfield><subfield code="c">XD-US</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-29T</subfield><subfield code="a">DE-20</subfield><subfield code="a">DE-739</subfield><subfield code="a">DE-11</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="084" ind1=" " ind2=" "><subfield code="a">ST 300</subfield><subfield code="0">(DE-625)143650:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Michelucci, Umberto</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1170709281</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Applied deep learning</subfield><subfield code="b">a case-based approach to understanding deep neural networks</subfield><subfield code="c">Umberto Michelucci</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">New York</subfield><subfield code="b">Apress</subfield><subfield code="c">[2018]</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xxi, 410 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</subfield><subfield code="c">25.4 cm x 17.8 cm</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="490" ind1="0" ind2=" "><subfield code="a">For professionals by professionals</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Auf der Coverrückseite: Shelve in: Programming languages / Python, user level: Intermediate - advanced</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="653" ind1=" " ind2=" "><subfield code="a">UMA</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Convolutional Neural Networks</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Deep Learning</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Dropout</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Neuron Activation Functions</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Python</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Recursive Neural Networks</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Regularization</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Skilearn</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">TensorFlow</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">UM</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">UN</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">UMA</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><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="710" ind1="2" ind2=" "><subfield code="a">Apress L.P.</subfield><subfield code="0">(DE-588)1065538766</subfield><subfield code="4">pbl</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Online-Ausgabe</subfield><subfield code="z">978-1-4842-3790-8</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">X:MVB</subfield><subfield code="q">text/html</subfield><subfield code="u">http://deposit.dnb.de/cgi-bin/dokserv?id=5dd6ec1196b34c58b7e9d5eae79fa300&prov=M&dok_var=1&dok_ext=htm</subfield><subfield code="3">Inhaltstext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">X:MVB</subfield><subfield code="u">http://www.springer.com/</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=030632589&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:BVB01-030632589</subfield></datafield></record></collection> |
id | DE-604.BV045244452 |
illustrated | Illustrated |
indexdate | 2025-02-13T07:00:23Z |
institution | BVB |
institution_GND | (DE-588)1065538766 |
isbn | 9781484237892 1484237897 |
language | English |
oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-030632589 |
oclc_num | 1060778685 |
open_access_boolean | |
owner | DE-29T DE-20 DE-739 DE-11 |
owner_facet | DE-29T DE-20 DE-739 DE-11 |
physical | xxi, 410 Seiten Illustrationen, Diagramme 25.4 cm x 17.8 cm |
publishDate | 2018 |
publishDateSearch | 2018 |
publishDateSort | 2018 |
publisher | Apress |
record_format | marc |
series2 | For professionals by professionals |
spelling | Michelucci, Umberto Verfasser (DE-588)1170709281 aut Applied deep learning a case-based approach to understanding deep neural networks Umberto Michelucci New York Apress [2018] xxi, 410 Seiten Illustrationen, Diagramme 25.4 cm x 17.8 cm txt rdacontent n rdamedia nc rdacarrier For professionals by professionals Auf der Coverrückseite: Shelve in: Programming languages / Python, user level: Intermediate - advanced Deep Learning (DE-588)1135597375 gnd rswk-swf UMA Convolutional Neural Networks Deep Learning Dropout Neuron Activation Functions Python Recursive Neural Networks Regularization Skilearn TensorFlow UM UN Deep Learning (DE-588)1135597375 s DE-604 Apress L.P. (DE-588)1065538766 pbl Erscheint auch als Online-Ausgabe 978-1-4842-3790-8 X:MVB text/html http://deposit.dnb.de/cgi-bin/dokserv?id=5dd6ec1196b34c58b7e9d5eae79fa300&prov=M&dok_var=1&dok_ext=htm Inhaltstext X:MVB http://www.springer.com/ 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=030632589&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
spellingShingle | Michelucci, Umberto Applied deep learning a case-based approach to understanding deep neural networks Deep Learning (DE-588)1135597375 gnd |
subject_GND | (DE-588)1135597375 |
title | Applied deep learning a case-based approach to understanding deep neural networks |
title_auth | Applied deep learning a case-based approach to understanding deep neural networks |
title_exact_search | Applied deep learning a case-based approach to understanding deep neural networks |
title_full | Applied deep learning a case-based approach to understanding deep neural networks Umberto Michelucci |
title_fullStr | Applied deep learning a case-based approach to understanding deep neural networks Umberto Michelucci |
title_full_unstemmed | Applied deep learning a case-based approach to understanding deep neural networks Umberto Michelucci |
title_short | Applied deep learning |
title_sort | applied deep learning a case based approach to understanding deep neural networks |
title_sub | a case-based approach to understanding deep neural networks |
topic | Deep Learning (DE-588)1135597375 gnd |
topic_facet | Deep Learning |
url | http://deposit.dnb.de/cgi-bin/dokserv?id=5dd6ec1196b34c58b7e9d5eae79fa300&prov=M&dok_var=1&dok_ext=htm http://www.springer.com/ http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=030632589&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
work_keys_str_mv | AT michelucciumberto applieddeeplearningacasebasedapproachtounderstandingdeepneuralnetworks AT apresslp applieddeeplearningacasebasedapproachtounderstandingdeepneuralnetworks |