HOME > Detail View

Detail View

Guide to convolutional neural networks [electronic resource] : a practical application to traffic-sign detection and classification

Guide to convolutional neural networks [electronic resource] : a practical application to traffic-sign detection and classification

Material type
E-Book(소장)
Personal Author
Habibi Aghdam, Hamed. Jahani Heravi, Elnaz.
Title Statement
Guide to convolutional neural networks [electronic resource] : a practical application to traffic-sign detection and classification / Hamed Habibi Aghdam, Elnaz Jahani Heravi.
Publication, Distribution, etc
Cham :   Springer,   c2017.  
Physical Medium
1 online resource (xxiii, 282 p.) : ill. (some col.).
ISBN
9783319575490 9783319575506 (e-book)
요약
This must-read text/reference introduces the fundamental concepts of convolutional neural networks (ConvNets), offering practical guidance on using libraries to implement ConvNets in applications of traffic sign detection and classification. The work presents techniques for optimizing the computational efficiency of ConvNets, as well as visualization techniques to better understand the underlying processes. The proposed models are also thoroughly evaluated from different perspectives, using exploratory and quantitative analysis. Topics and features: Explains the fundamental concepts behind training linear classifiers and feature learning Discusses the wide range of loss functions for training binary and multi-class classifiers Illustrates how to derive ConvNets from fully connected neural networks, and reviews different techniques for evaluating neural networks Presents a practical library for implementing ConvNets, explaining how to use a Python interface for the library to create and assess neural networks Describes two real-world examples of the detection and classification of traffic signs using deep learning methods Examines a range of varied techniques for visualizing neural networks, using a Python interface Provides self-study exercises at the end of each chapter, in addition to a helpful glossary, with relevant Python scripts supplied at an associated website This self-contained guide will benefit those who seek to both understand the theory behind deep learning, and to gain hands-on experience in implementing ConvNets in practice. As no prior background knowledge in the field is required to follow the material, the book is ideal for all students of computer vision and machine learning, and will also be of great interest to practitioners working on autonomous cars and advanced driver assistance systems.
General Note
Title from e-Book title page.  
Content Notes
Traffic Sign Detection and Recognition -- Pattern Classification -- Convolutional Neural Networks -- Caffe Library -- Classification of Traffic Signs -- Detecting Traffic Signs -- Visualizing Neural Networks -- Appendix A: Gradient Descend.
Bibliography, Etc. Note
Includes bibliographical references and index.
이용가능한 다른형태자료
Issued also as a book.  
Subject Added Entry-Topical Term
Optical pattern recognition. Computer network architectures. Natural language processing (Computer science). Engineering.
Short cut
URL
000 00000cam u2200205 a 4500
001 000046011806
005 20200122094949
006 m d
007 cr
008 200107s2017 sz a ob 001 0 eng d
020 ▼a 9783319575490
020 ▼a 9783319575506 (e-book)
040 ▼a 211009 ▼c 211009 ▼d 211009
050 4 ▼a Q337.5
082 0 4 ▼a 006.32 ▼2 23
084 ▼a 006.32 ▼2 DDCK
090 ▼a 006.32
100 1 ▼a Habibi Aghdam, Hamed.
245 1 0 ▼a Guide to convolutional neural networks ▼h [electronic resource] : ▼b a practical application to traffic-sign detection and classification / ▼c Hamed Habibi Aghdam, Elnaz Jahani Heravi.
260 ▼a Cham : ▼b Springer, ▼c c2017.
300 ▼a 1 online resource (xxiii, 282 p.) : ▼b ill. (some col.).
500 ▼a Title from e-Book title page.
504 ▼a Includes bibliographical references and index.
505 0 ▼a Traffic Sign Detection and Recognition -- Pattern Classification -- Convolutional Neural Networks -- Caffe Library -- Classification of Traffic Signs -- Detecting Traffic Signs -- Visualizing Neural Networks -- Appendix A: Gradient Descend.
520 ▼a This must-read text/reference introduces the fundamental concepts of convolutional neural networks (ConvNets), offering practical guidance on using libraries to implement ConvNets in applications of traffic sign detection and classification. The work presents techniques for optimizing the computational efficiency of ConvNets, as well as visualization techniques to better understand the underlying processes. The proposed models are also thoroughly evaluated from different perspectives, using exploratory and quantitative analysis. Topics and features: Explains the fundamental concepts behind training linear classifiers and feature learning Discusses the wide range of loss functions for training binary and multi-class classifiers Illustrates how to derive ConvNets from fully connected neural networks, and reviews different techniques for evaluating neural networks Presents a practical library for implementing ConvNets, explaining how to use a Python interface for the library to create and assess neural networks Describes two real-world examples of the detection and classification of traffic signs using deep learning methods Examines a range of varied techniques for visualizing neural networks, using a Python interface Provides self-study exercises at the end of each chapter, in addition to a helpful glossary, with relevant Python scripts supplied at an associated website This self-contained guide will benefit those who seek to both understand the theory behind deep learning, and to gain hands-on experience in implementing ConvNets in practice. As no prior background knowledge in the field is required to follow the material, the book is ideal for all students of computer vision and machine learning, and will also be of great interest to practitioners working on autonomous cars and advanced driver assistance systems.
530 ▼a Issued also as a book.
538 ▼a Mode of access: World Wide Web.
650 0 ▼a Optical pattern recognition.
650 0 ▼a Computer network architectures.
650 0 ▼a Natural language processing (Computer science).
650 0 ▼a Engineering.
700 1 ▼a Jahani Heravi, Elnaz.
856 4 0 ▼u https://oca.korea.ac.kr/link.n2s?url=https://doi.org/10.1007/978-3-319-57550-6
945 ▼a KLPA
991 ▼a E-Book(소장)

Holdings Information

No. Location Call Number Accession No. Availability Due Date Make a Reservation Service
No. 1 Location Main Library/e-Book Collection/ Call Number CR 006.32 Accession No. E14018747 Availability Loan can not(reference room) Due Date Make a Reservation Service M

Contents information

Table of Contents

CONTENTS
1 Traffic Sign Detection and Recognition = 1
 1.1 Introduction = 1
 1.2 Challenges = 2
 1.3 Previous Work = 5
  1.3.1 Template Matching = 5
  1.3.2 Hand-Crafted Features = 5
  1.3.3 Feature Learning = 7
  1.3.4 ConvNets = 10
 1.4 Summary = 12
 References = 12
2 Pattern Classification = 15
 2.1 Formulation = 16
  2.1.1 K-Nearest Neighbor = 17
 2.2 Linear Classifier = 20
  2.2.1 Training a Linear Classifier = 22
  2.2.2 Hinge Loss = 30
  2.2.3 Logistic Regression = 34
  2.2.4 Comparing Loss Function = 37
 2.3 Multiclass Classification = 41
  2.3.1 One Versus One = 41
  2.3.2 One Versus Rest = 44
  2.3.3 Multiclass Hinge Loss = 46
  2.3.4 Multinomial Logistic Function = 48
 2.4 Feature Extraction = 51
 2.5 Learning UðxÞ = 58
 2.6 Artificial Neural Networks = 61
  2.6.1 Backpropagation = 65
  2.6.2 Activation Functions = 71
  2.6.3 Role of Bias = 78
  2.6.4 Initialization = 79
  2.6.5 How to Apply on Images = 79
 2.7 Summary = 81
 2.8 Exercises = 82
 References = 83
3 Convolutional Neural Networks = 85
 3.1 Deriving Convolution from a Fully Connected Layer = 85
  3.1.1 Role of Convolution = 90
  3.1.2 Backpropagation of Convolution Layers = 92
  3.1.3 Stride in Convolution = 94
 3.2 Pooling = 95
  3.2.1 Backpropagation in Pooling Layer = 97
 3.3 LeNet = 98
 3.4 AlexNet = 100
 3.5 Designing a ConvNet = 101
  3.5.1 ConvNet Architecture = 102
  3.5.2 Software Libraries = 103
  3.5.3 Evaluating a ConvNet = 105
 3.6 Training a ConvNet = 111
  3.6.1 Loss Function = 112
  3.6.2 Initialization = 113
  3.6.3 Regularization = 115
  3.6.4 Learning Rate Annealing = 121
 3.7 Analyzing Quantitative Results = 124
 3.8 Other Types of Layers = 126
  3.8.1 Local Response Normalization = 126
  3.8.2 Spatial Pyramid Pooling = 127
  3.8.3 Mixed Pooling = 127
  3.8.4 Batch Normalization = 127
 3.9 Summary = 128
 3.10 Exercises = 128
 References = 129
4 Caffe Library = 131
 4.1 Introduction = 131
 4.2 Installing Caffe = 132
 4.3 Designing Using Text Files = 132
  4.3.1 Providing Data = 137
  4.3.2 Convolution Layers = 139
  4.3.3 Initializing Parameters = 141
  4.3.4 Activation Layer = 142
  4.3.5 Pooling Layer = 144
  4.3.6 Fully Connected Layer = 145
  4.3.7 Dropout Layer = 146
  4.3.8 Classification and Loss Layers = 146
 4.4 Training a Network = 152
 4.5 Designing in Python = 154
 4.6 Drawing Architecture of Network = 157
 4.7 Training Using Python = 157
 4.8 Evaluating Using Python = 158
 4.9 Save and Restore Networks = 161
 4.10 Python Layer in Caffe = 162
 4.11 Summary = 164
 4.12 Exercises = 164
 Reference = 166
5 Classification of Traffic Signs = 167
 5.1 Introduction = 167
 5.2 Related Work = 169
  5.2.1 Template Matching = 170
  5.2.2 Hand-Crafted Features = 170
  5.2.3 Sparse Coding = 171
  5.2.4 Discussion = 171
  5.2.5 ConvNets = 172
 5.3 Preparing Dataset = 173
  5.3.1 Splitting Data = 174
  5.3.2 Augmenting Dataset = 177
  5.3.3 Static Versus One-the-Fly Augmenting = 185
  5.3.4 Imbalanced Dataset = 185
  5.3.5 Preparing the GTSRB Dataset = 187
 5.4 Analyzing Training/Validation Curves = 188
 5.5 ConvNets for Classification of Traffic Signs = 189
 5.6 Ensemble of ConvNets = 199
  5.6.1 Combining Models = 200
  5.6.2 Training Different Models = 201
  5.6.3 Creating Ensemble = 202
 5.7 Evaluating Networks = 203
  5.7.1 Misclassified Images = 208
  5.7.2 Cross-Dataset Analysis and Transfer Learning = 209
  5.7.3 Stability of ConvNet = 214
  5.7.4 Analyzing by Visualization = 217
 5.8 Analyzing by Visualizing = 217
  5.8.1 Visualizing Sensitivity = 218
  5.8.2 Visualizing the Minimum Perception = 219
  5.8.3 Visualizing Activations = 220
 5.9 More Accurate ConvNet = 222
  5.9.1 Evaluation = 224
  5.9.2 Stability Against Noise = 226
  5.9.3 Visualization = 229
 5.10 Summary = 230
 5.11 Exercises = 231
 References = 232
6 Detecting Traffic Signs = 235
 6.1 Introduction = 235
 6.2 ConvNet for Detecting Traffic Signs = 236
 6.3 Implementing Sliding Window Within the ConvNet = 239
 6.4 Evaluation = 243
 6.5 Summary = 246
 6.6 Exercises = 246
 References = 246
7 Visualizing Neural Networks = 247
 7.1 Introduction = 247
 7.2 Data-Oriented Techniques = 248
  7.2.1 Tracking Activation = 248
  7.2.2 Covering Mask = 248
  7.2.3 Embedding = 249
 7.3 Gradient-Based Techniques = 249
  7.3.1 Activation Maximization = 250
  7.3.2 Activation Saliency = 253
 7.4 Inverting Representation = 254
 7.5 Summary = 257
 7.6 Exercises = 257
 References = 258
Appendix A : Gradient Descend = 259
Glossary = 275
Index = 279

New Arrivals Books in Related Fields

Cartwright, Hugh M. (2021)
한국소프트웨어기술인협회. 빅데이터전략연구소 (2021)