國立高雄大學圖資館 |

Language: English

Back

Applied deep learninga case-based ap...

Michelucci, Umberto.

Applied deep learninga case-based approach to understanding deep neural networks /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Applied deep learningby Umberto Michelucci.
Reminder of title:	a case-based approach to understanding deep neural networks /
Author:	Michelucci, Umberto.
Published:	Berkeley, CA :Apress :2018.
Description:	xxi, 410 p. :ill., digital ;24 cm.
Contained By:	Springer eBooks
Subject:	Machine learning.
Online resource:	https://doi.org/10.1007/978-1-4842-3790-8
ISBN:	9781484237908$q(electronic bk.)

Applied deep learninga case-based approach to understanding deep neural networks /
Michelucci, Umberto.

Applied deep learninga case-based approach to understanding deep neural networks /[electronic resource] :by Umberto Michelucci. - Berkeley, CA :Apress :2018. - xxi, 410 p. :ill., digital ;24 cm.

Chapter 1: Introduction -- Chapter 2: Single Neurons -- Chapter 3: Fully connected Neural Network with more neurons -- Chapter 4: Neural networks error analysis -- Chapter 5: Dropout technique -- Chapter 6: Hyper parameters tuning -- Chapter 7: Tensorflow and optimizers (Gradient descent, Adam, momentum, etc.) -- Chapter 8: Convolutional Networks and image recognition -- Chapter 9: Recurrent Neural Networks -- Chapter 10: A practical COMPLETE example from scratch (put everything together) -- Chapter 11: Logistic regression implement from scratch in Python without libraries.

Work with advanced topics in deep learning, such as optimization algorithms, hyper-parameter tuning, dropout, and error analysis as well as strategies to address typical problems encountered when training deep neural networks. You'll begin by studying the activation functions mostly with a single neuron (ReLu, sigmoid, and Swish), seeing how to perform linear and logistic regression using TensorFlow, and choosing the right cost function. The next section talks about more complicated neural network architectures with several layers and neurons and explores the problem of random initialization of weights. An entire chapter is dedicated to a complete overview of neural network error analysis, giving examples of solving problems originating from variance, bias, overfitting, and datasets coming from different distributions. Applied Deep Learning also discusses how to implement logistic regression completely from scratch without using any Python library except NumPy, to let you appreciate how libraries such as TensorFlow allow quick and efficient experiments. Case studies for each method are included to put into practice all theoretical information. You'll discover tips and tricks for writing optimized Python code (for example vectorizing loops with NumPy) You will: Implement advanced techniques in the right way in Python and TensorFlow Debug and optimize advanced methods (such as dropout and regularization) Carry out error analysis (to realize if one has a bias problem, a variance problem, a data offset problem, and so on) Set up a machine learning project focused on deep learning on a complex dataset.

ISBN: 9781484237908$q(electronic bk.)

Standard No.: 10.1007/978-1-4842-3790-8doiSubjects--Topical Terms:

188639
Machine learning.

LC Class. No.: Q325.5 / .M534 2018

Dewey Class. No.: 006.31

Applied deep learninga case-based approach to understanding deep neural networks /
LDR:03224nmm a2200325 a 4500 001 544127
003 DE-He213
005 20190306110140.0
006 m d
007 cr nn 008maaau
008 190430s2018 cau s 0 eng d
020 $a 9781484237908$q(electronic bk.)
020 $a 9781484237892$q(paper)
024 7 $a 10.1007/978-1-4842-3790-8 $2 doi
035 $a 978-1-4842-3790-8
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.5 $b .M534 2018
072 7 $a UMA $2 bicssc
072 7 $a COM014000 $2 bisacsh
072 7 $a UMA $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.5 $b .M623 2018
100 1 $a Michelucci, Umberto. $3 822624
245 1 0 $a Applied deep learning $h [electronic resource] : $b a case-based approach to understanding deep neural networks / $c by Umberto Michelucci.
260 $a Berkeley, CA : $b Apress : $b Imprint: Apress, $c 2018.
300 $a xxi, 410 p. : $b ill., digital ; $c 24 cm.
505 0 $a Chapter 1: Introduction -- Chapter 2: Single Neurons -- Chapter 3: Fully connected Neural Network with more neurons -- Chapter 4: Neural networks error analysis -- Chapter 5: Dropout technique -- Chapter 6: Hyper parameters tuning -- Chapter 7: Tensorflow and optimizers (Gradient descent, Adam, momentum, etc.) -- Chapter 8: Convolutional Networks and image recognition -- Chapter 9: Recurrent Neural Networks -- Chapter 10: A practical COMPLETE example from scratch (put everything together) -- Chapter 11: Logistic regression implement from scratch in Python without libraries.
520 $a Work with advanced topics in deep learning, such as optimization algorithms, hyper-parameter tuning, dropout, and error analysis as well as strategies to address typical problems encountered when training deep neural networks. You'll begin by studying the activation functions mostly with a single neuron (ReLu, sigmoid, and Swish), seeing how to perform linear and logistic regression using TensorFlow, and choosing the right cost function. The next section talks about more complicated neural network architectures with several layers and neurons and explores the problem of random initialization of weights. An entire chapter is dedicated to a complete overview of neural network error analysis, giving examples of solving problems originating from variance, bias, overfitting, and datasets coming from different distributions. Applied Deep Learning also discusses how to implement logistic regression completely from scratch without using any Python library except NumPy, to let you appreciate how libraries such as TensorFlow allow quick and efficient experiments. Case studies for each method are included to put into practice all theoretical information. You'll discover tips and tricks for writing optimized Python code (for example vectorizing loops with NumPy) You will: Implement advanced techniques in the right way in Python and TensorFlow Debug and optimize advanced methods (such as dropout and regularization) Carry out error analysis (to realize if one has a bias problem, a variance problem, a data offset problem, and so on) Set up a machine learning project focused on deep learning on a complex dataset.
650 0 $a Machine learning. $3 188639
650 0 $a Neural networks (Computer science) $3 181982
650 1 4 $a Computing Methodologies. $3 274528
650 2 4 $a Python. $3 763308
650 2 4 $a Open Source. $3 758930
650 2 4 $a Big Data. $3 760530
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer eBooks
856 4 0 $u https://doi.org/10.1007/978-1-4842-3790-8
950 $a Professional and Applied Computing (Springer-12059)