Atjaunināt sīkdatņu piekrišanu

E-grāmata: Machine Learning - A Journey To Deep Learning: With Exercises And Answers

(Univ De Lisboa, Portugal & Inesc-id, Portugal), (Univ De Lisboa, Portugal & Inesc-id, Portugal)
  • Formāts: 640 pages
  • Izdošanas datums: 26-Jan-2021
  • Izdevniecība: World Scientific Publishing Co Pte Ltd
  • Valoda: eng
  • ISBN-13: 9789811234071
Citas grāmatas par šo tēmu:
  • Formāts - PDF+DRM
  • Cena: 135,25 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Ielikt grozā
  • Pievienot vēlmju sarakstam
  • Šī e-grāmata paredzēta tikai personīgai lietošanai. E-grāmatas nav iespējams atgriezt un nauda par iegādātajām e-grāmatām netiek atmaksāta.
Machine Learning - A Journey To Deep Learning: With Exercises And AnswersPalielināt
  • Formāts: 640 pages
  • Izdošanas datums: 26-Jan-2021
  • Izdevniecība: World Scientific Publishing Co Pte Ltd
  • Valoda: eng
  • ISBN-13: 9789811234071
Citas grāmatas par šo tēmu:

DRM restrictions

  • Kopēšana (kopēt/ievietot):

    nav atļauts

  • Drukāšana:

    nav atļauts

  • Lietošana:

    Digitālo tiesību pārvaldība (Digital Rights Management (DRM))
    Izdevējs ir piegādājis šo grāmatu šifrētā veidā, kas nozīmē, ka jums ir jāinstalē bezmaksas programmatūra, lai to atbloķētu un lasītu. Lai lasītu šo e-grāmatu, jums ir jāizveido Adobe ID. Vairāk informācijas šeit. E-grāmatu var lasīt un lejupielādēt līdz 6 ierīcēm (vienam lietotājam ar vienu un to pašu Adobe ID).

    Nepieciešamā programmatūra
    Lai lasītu šo e-grāmatu mobilajā ierīcē (tālrunī vai planšetdatorā), jums būs jāinstalē šī bezmaksas lietotne: PocketBook Reader (iOS / Android)

    Lai lejupielādētu un lasītu šo e-grāmatu datorā vai Mac datorā, jums ir nepieciešamid Adobe Digital Editions (šī ir bezmaksas lietotne, kas īpaši izstrādāta e-grāmatām. Tā nav tas pats, kas Adobe Reader, kas, iespējams, jau ir jūsu datorā.)

    Jūs nevarat lasīt šo e-grāmatu, izmantojot Amazon Kindle.

This unique compendium discusses some core ideas for the development and implementation of machine learning from three different perspectives the statistical perspective, the artificial neural network perspective and the deep learning methodology.The useful reference text represents a solid foundation in machine learning and should prepare readers to apply and understand machine learning algorithms as well as to invent new machine learning methods. It tells a story outgoing from a perceptron to deep learning highlighted with concrete examples, including exercises and answers for the students.Related Link(s)
Preface vii
1 Introduction
1(36)
1.1 What is Machine Learning
2(5)
1.1.1 Symbolical Learning
2(1)
1.1.2 Statistical Machine Learning
3(3)
1.1.3 Supervised and Unsupervised Machine Learning
6(1)
1.2 It all began with the Perceptron
7(12)
1.2.1 Artificial Neuron
8(2)
1.2.2 Perceptron
10(7)
1.2.3 XOfl-Problem
17(2)
1.3 Road to Deep Learning
19(1)
1.3.1 Backpropagation
19(1)
1.4 Synopsis
19(4)
1.4.1 Content
21(2)
1.5 Exercises and Answers
23(14)
2 Probability and Information
37(68)
2.1 Probability Theory
38(8)
2.1.1 Conditional probability
39(1)
2.1.2 Law of Total Probability
40(1)
2.1.3 Bayes's rule
41(2)
2.1.4 Expectation
43(1)
2.1.5 Covariance
44(2)
2.2 Distribution
46(8)
2.2.1 Gaussian Distribution
46(5)
2.2.2 Laplace Distribution
51(1)
2.2.3 Bernoulli Distribution
51(3)
2.3 Information Theory
54(9)
2.3.1 Surprise and Information
55(1)
2.3.2 Entropy
56(6)
2.3.3 Conditional Entropy
62(1)
2.3.4 Relative Entropy
62(1)
2.3.5 Mutual Information
62(1)
2.3.6 Relationship
63(1)
2.4 Cross Entropy
63(5)
2.5 Exercises and Answers
68(37)
3 Linear Algebra and Optimization
105(26)
3.1 Vectors
106(5)
3.1.1 Norm
106(1)
3.1.2 Distance function
107(1)
3.1.3 Scalar Product
108(1)
3.1.4 Linear Independent Vectors
109(1)
3.1.5 Matrix Operations
110(1)
3.1.6 Tensor Product
110(1)
3.1.7 Hadamard product
111(1)
3.1.8 Element-wise division
111(1)
3.2 Matrix Calculus
111(1)
3.2.1 Gradient
111(1)
3.2.2 Jacobian
112(1)
3.2.3 Hessian Matrix
113(1)
3.3 Gradient based Numerical Optimization
113(7)
3.3.1 Gradient descent
113(3)
3.3.2 Newton's Method
116(2)
3.3.3 Second and First Order Optimization
118(2)
3.4 Dilemmas in Machine Learning
120(2)
3.4.1 The Curse of Dimensionality
120(2)
3.4.2 Numerical Computation
122(1)
3.5 Exercises and Answers
122(9)
4 Linear and Nonlinear Regression
131(56)
4.1 Linear Regression
132(9)
4.1.1 Regression of a Line
132(1)
4.1.2 Multiple Linear Regression
132(2)
4.1.3 Design Matrix
134(1)
4.1.4 Squared-Error
134(1)
4.1.5 Closed-Form Solution
135(1)
4.1.6 Example
136(2)
4.1.7 Moore-Penrose Matrix
138(3)
4.2 Linear Basis Function Models
141(2)
4.2.1 Example Logarithmic Curve
142(1)
4.2.2 Example Polynomial Regression
142(1)
4.3 Model selection
143(3)
4.4 Bayesian Regression
146(9)
4.4.1 Maximizing the Likelihood or the Posterior
147(1)
4.4.2 Bayesian Learning
148(3)
4.4.3 Maximizing a posteriori
151(1)
4.4.4 Relation between Regularized Least-Squares and MAP
151(2)
4.4.5 LASSO Regularizer
153(2)
4.5 Linear Regression for classification
155(1)
4.6 Exercises and Answers
156(31)
5 Perceptron
187(36)
5.1 Linear Regression and Linear Artificial Neuron
188(4)
5.1.1 Regularization
191(1)
5.1.2 Stochastic gradient descent
191(1)
5.2 Continuous Differentiable Activation Functions
192(8)
5.2.1 Sigmoid Activation Functions
193(1)
5.2.2 Perceptron with sgno
194(2)
5.2.3 Cross Entropy Loss Function
196(3)
5.2.4 Linear Unit versus Sigmoid Unit
199(1)
5.2.5 Logistic Regression
199(1)
5.3 Multiclass Linear Discriminant
200(6)
5.3.1 Cross Entropy Loss Function for softmax
203(2)
5.3.2 Logistic Regression Algorithm
205(1)
5.4 Multilayer Perceptron
206(1)
5.5 Exercises and Answers
207(16)
6 Multilayer Perceptron
223(28)
6.1 Motivations
224(1)
6.2 Networks with Hidden Nonlinear Layers
224(10)
6.2.1 Backpropagation
226(2)
6.2.2 Example
228(4)
6.2.3 Activation Function
232(2)
6.3 Cross Entropy Error Function
234(6)
6.3.1 Backpropagation
235(2)
6.3.2 Comparison
237(1)
6.3.3 Computing Power
238(1)
6.3.4 Generalization
238(2)
6.4 Training
240(4)
6.4.1 Overfitting
241(1)
6.4.2 Early-Stopping Rule
241(1)
6.4.3 Regularization
242(2)
6.5 Deep Learning and Backpropagation
244(1)
6.6 Exercises and Answers
245(6)
7 Learning Theory
251(42)
7.1 Supervised Classification Problem
252(1)
7.2 Probability of a bad sample
253(3)
7.3 Infinite hypotheses set
256(2)
7.4 The VC Dimension
258(1)
7.5 A Fundamental Trade-off
259(3)
7.6 Computing VC Dimension
262(5)
7.6.1 The VC Dimension of a Perceptron
264(3)
7.6.2 A Heuristic way to measure hypotheses space complexity
267(1)
7.7 The Regression Problem
267(8)
7.7.1 Example
270(5)
7.8 Exercises and Answers
275(18)
8 Model Selection
293(16)
8.1 The confusion matrix
294(1)
8.1.1 Precision and Recall
294(1)
8.1.2 Several Classes
295(1)
8.2 Validation Set and Test Set
295(2)
8.3 Cross-Validation
297(1)
8.4 Minimum-Description-Length
298(5)
8.4.1 Occam's razor
299(1)
8.4.2 Kolmogorov complexity theory
299(1)
8.4.3 Learning as Data Compression
300(1)
8.4.4 Two-part code MDL principle
301(2)
8.5 Paradox of Deep Learning Complexity
303(3)
8.6 Exercises and Answers
306(3)
9 Clustering
309(68)
9.1 Introduction
310(1)
9.2 if-means Clustering
310(5)
9.2.1 Standard X-means
313(1)
9.2.2 Sequential k-means
314(1)
9.3 Mixture of Gaussians
315(9)
9.3.1 EM for Gaussian Mixtures
317(3)
9.3.2 Algorithm: EM for Gaussian mixtures
320(2)
9.3.3 Example
322(2)
9.4 EM and k-means Clustering
324(1)
9.5 Exercises and Answers
324(53)
10 Radial Basis Networks
377(14)
10.1 Cover's theorem
378(1)
10.1.1 Cover's theorem on the separability (1965)
379(1)
10.2 Interpolation Problem
379(2)
10.2.1 Micchelli's Theorem
381(1)
10.3 Radial Basis Function Networks
381(3)
10.3.1 Modifications of Radial Basis Function Networks
382(1)
10.3.2 Interpretation of Hidden Units
383(1)
10.4 Exercises and Answers
384(7)
11 Support Vector Machines
391(32)
11.1 Margin
392(2)
11.2 Optimal Hyperplane for Linear Separable Patterns
394(1)
11.3 Support Vectors
395(1)
11.4 Quadratic Optimization for Finding the Optimal Hyperplane
396(4)
11.4.1 Dual Problem
397(3)
11.5 Optimal Hyperplane for Non-separable Patterns
400(1)
11.5.1 Dual Problem
401(1)
11.6 Support Vector Machine as a Kernel Machine
401(7)
11.6.1 Kernel Trick
403(1)
11.6.2 Dual Problem
404(1)
11.6.3 Classification
405(3)
11.7 Constructing Kernels
408(2)
11.7.1 Gaussian Kernel
409(1)
11.7.2 Sigmoidal Kernel
409(1)
11.7.3 Generative mode Kernels
410(1)
11.8 Conclusion
410(2)
11.8.1 SVMs, MLPs and RBFNs
411(1)
11.9 Exercises and Answers
412(11)
12 Deep Learning
423(66)
12.1 Introduction
424(2)
12.1.1 Loss Function
424(1)
12.1.2 Mini-Batch
425(1)
12.2 Why Deep Networks?
426(3)
12.2.1 Hierarchical Organization
427(1)
12.2.2 Boolean Functions
427(1)
12.2.3 Curse of dimensionality
427(1)
12.2.4 Local Minima
428(1)
12.2.5 Can represent big training sets
428(1)
12.2.6 Efficient Model Selection
428(1)
12.2.7 Criticism of Deep Neural Networks
429(1)
12.3 Vanishing Gradients Problem
429(7)
12.3.1 Rectified Linear Unit (ReL U)
430(3)
12.3.2 Residual Learning
433(1)
12.3.3 Batch Normalization
434(2)
12.4 Regularization by Dropout
436(1)
12.5 Weight Initialization
437(1)
12.6 Faster Optimizers
437(4)
12.6.1 Momentum
438(1)
12.6.2 Nestrov Momentum
438(1)
12.6.3 AdaGrad
438(1)
12.6.4 RMSProp
439(1)
12.6.5 Adam
439(1)
12.6.6 Notation
440(1)
12.7 Transfer Learning
441(1)
12.8 Conclusion
441(1)
12.9 Exercises and Answers
442(47)
13 Convolutional Networks
489(32)
13.1 Hierarchical Networks
490(6)
13.1.1 Biological Vision
490(1)
13.1.2 Neocognitron
490(2)
13.1.3 Map transformation cascade
492(4)
13.2 Convolutional Neural Networks
496(11)
13.2.1 CNNs and Kernels in Image Processing
499(7)
13.2.2 Data Augmentation
506(1)
13.2.3 Case Studies
506(1)
13.3 Exercises and Answers
507(14)
14 Recurrent Networks
521(54)
14.1 Sequence Modelling
522(2)
14.2 Recurrent Neural Networks
524(7)
14.2.1 Elman recurrent neural networks
524(2)
14.2.2 Jordan recurrent neural networks
526(1)
14.2.3 Single Output
527(2)
14.2.4 Backpropagation Trough Time
529(2)
14.2.5 Deep Recurrent Networks
531(1)
14.3 Long Short Term Memory
531(4)
14.4 Process Sequences
535(2)
14.5 Exercises and Answers
537(38)
15 Autoencoders
575(34)
15.1 Eigenvectors and Eigenvalues
576(1)
15.2 The Karhunen-Loeve transform
576(6)
15.2.1 Principal component analysis
578(4)
15.3 Singular Value Decomposition
582(2)
15.3.1 Example
583(1)
15.3.2 Pseudoinverse
583(1)
15.3.3 SVD and PCA
584(1)
15.4 Autoencoders
584(2)
15.5 Undercomplete Autoencoders
586(1)
15.6 Overcomplete Autoencoders
587(3)
15.6.1 Denoising Autoencoders
589(1)
15.7 Exercises and Answers
590(19)
16 Epilogue
609(4)
Bibliography 613(8)
Index 621
Biežāk uzdotie jautājumi par e-grāmatām Biežāk uzdotie jautājumi par e-grāmatām
Permanent link: https://www.kriso.lv/db/97898112340712e.html