Muutke küpsiste eelistusi

Math for Deep Learning: What You Need to Know to Understand Neural Networks [Pehme köide]

4.49/5 (65 hinnangut Goodreads-ist)
  • Formaat: Paperback / softback, 344 pages, kõrgus x laius: 235x178 mm
  • Ilmumisaeg: 07-Dec-2021
  • Kirjastus: No Starch Press,US
  • ISBN-10: 1718501900
  • ISBN-13: 9781718501904
Teised raamatud teemal:
Math for Deep Learning: What You Need to Know to Understand Neural NetworksSuurem pilt
  • Formaat: Paperback / softback, 344 pages, kõrgus x laius: 235x178 mm
  • Ilmumisaeg: 07-Dec-2021
  • Kirjastus: No Starch Press,US
  • ISBN-10: 1718501900
  • ISBN-13: 9781718501904
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781718501904.html
Märksõnad:
Math for Deep Learning provides the essential math you need to understand deep learning discussions, explore more complex implementations, and better use the deep learning toolkits.

With Math for Deep Learning, you'll learn the essential mathematics used by and as a background for deep learning. 

You’ll work through Python examples to learn key deep learning related topics in probability, statistics, linear algebra, differential calculus, and matrix calculus as well as how to implement data flow in a neural network, backpropagation, and gradient descent. You’ll also use Python to work through the mathematics that underlies those algorithms and even build a fully-functional neural network.

In addition you’ll find coverage of gradient descent including variations commonly used by the deep learning community: SGD, Adam, RMSprop, and Adagrad/Adadelta.

Arvustused

"An excellent resource for anyone looking to gain a solid foundation in the mathematics underlying deep learning algorithms. The book is accessible, well-organized, and provides clear explanations and practical examples of key mathematical concepts. I highly recommend it to anyone interested in this field." Daniel Gutierrez, insideBIGDATA

"Ronald T. Kneusel has written a handy and compact guide to the mathematics of deep learning. It will be a well-worn reference for equations and algorithms for the student, scientist, and practitioner of neural networks and machine learning. Complete with equations, figures and even sample code in Python, this book is a wonderful mathematical introduction for the reader." David S. Mazel, Senior Engineer, Regulus-Group

"What makes Math for Deep Learning a stand-out, is that it focuses on providing a sufficient mathematical foundation for deep learning, rather than attempting to cover all of deep learning, and introduce the needed math along the way. Those eager to master deep learning are sure to benefit from this foundation-before-house approach." Ed Scott, Ph.D., Solutions Architect & IT Enthusiast

Foreword xvii
Acknowledgments xxi
Introduction xxiii
Who Is This Book For? xxiv
About This Book xxiv
1 Setting the Stage
1(16)
Installing the Toolkits
2(1)
Linux
2(1)
macOS
3(1)
Windows
3(1)
NumPy
4(1)
Defining Arrays
5(1)
Data Types
5(1)
2D Arrays
6(1)
Zeros and Ones
7(1)
Advanced Indexing
7(3)
Reading and Writing to Disk
10(1)
SciPy
11(1)
Matplotlib
12(2)
Scikit-Learn
14(1)
Summary
15(2)
2 Probability
17(24)
Basic Concepts
18(1)
Sample Space and Events
18(1)
Random Variables
19(1)
Humans Are Bad at Probability
19(2)
The Rules of Probability
21(1)
Probability of an Event
21(3)
Sum Rule
24(1)
Product Rule
25(1)
Sum Rule Revisited
25(1)
The Birthday Paradox
26(4)
Conditional Probability
30(1)
Total Probability
31(1)
Joint and Marginal Probability
32(1)
Joint Probability Tables
33(4)
Chain Rule for Probability
37(2)
Summary
39(2)
3 More Probability
41(26)
Probability Distributions
41(1)
Histograms and Probabilities
42(3)
Discrete Probability Distributions
45(6)
Continuous Probability Distributions
51(4)
Central Limit Theorem
55(3)
The Law of Large Numbers
58(1)
Bayes' Theorem
59(1)
Cancer or Not Redux
60(1)
Updating the Prior
61(1)
Bayes' Theorem in Machine Learning
62(3)
Summary
65(2)
4 Statistics
67(36)
Types of Data
68(1)
Nominal Data
68(1)
Ordinal Data
68(1)
Interval Data
68(1)
Ratio Data
68(1)
Using Nominal Data in Deep Learning
69(1)
Summary Statistics
70(1)
Means and Median
70(4)
Measures of Variation
74(4)
Quantiles and Box Plots
78(5)
Missing Data
83(2)
Correlation
85(1)
Pearson Correlation
86(4)
Spearman Correlation
90(2)
Hypothesis Testing
92(1)
Hypotheses
93(2)
The t-test
95(4)
The Mann-Whitney U Test
99(3)
Summary
102(1)
5 Linear Algebra
103(24)
Scalars, Vectors, Matrices, and Tensors
104(1)
Scalers
104(1)
Vectors
104(1)
Matrices
105(1)
Tensors
106(3)
Arithmetic with Tensors
109(1)
Array Operations
109(2)
Vector Operations
111(9)
Matrix Multiplication
120(5)
Kronecker Product
125(1)
Summary
126(1)
6 More Linear Algebra
127(36)
Square Matrices
128(1)
Why Square Matrices?
128(1)
Transpose, Trace, and Powers
129(2)
Special Square Matrices
131(1)
The Identity Matrix
132(2)
Determinants
134(3)
Inverses
137(2)
Symmetric, Orthogonal, and Unitary Matrices
139(1)
Definiteness of a Symmetric Matrix
140(1)
Eigenvectors and Eigenvalues
141(1)
Finding Eigenvalues and Eigenvectors
141(3)
Vector Norms and Distance Metrics
144(1)
L-Norms and Distance Metrics
145(1)
Covariance Matrices
146(2)
Mahalanobis Distance
148(3)
Kullback-Leibler Divergence
151(2)
Principal Component Analysis
153(4)
Singular Value Decomposition and Pseudoinverse
157(1)
SVD in Action
158(1)
Two Applications
159(2)
Summary
161(2)
7 Differential Calculus
163(30)
Slope
164(1)
Derivatives
165(1)
A Formal Definition
165(2)
Basic Rules
167(5)
Rules for Trigonometric Functions
172(3)
Rules for Exponentials and Logarithms
175(2)
Minima and Maxima of Functions
177(4)
Partial Derivatives
181(2)
Mixed Partial Derivatives
183(1)
The Chain Rule for Partial Derivatives
184(2)
Gradients
186(1)
Calculating the Gradient
186(3)
Visualizing the Gradient
189(2)
Summary
191(2)
8 Matrix Calculus
193(28)
The Formulas
194(1)
A Vector Function by a Scalar Argument
194(2)
A Scalar Function by a Vector Argument
196(1)
A Vector Function by a Vector
197(1)
A Matrix Function by a Scalar
198(1)
A Scalar Function by a Matrix
198(1)
The Identities
199(1)
A Scalar Function by a Vector
199(3)
A Vector Function by a Scalar
202(1)
A Vector Function by a Vector
203(1)
A Scalar Function by a Matrix
203(2)
Jacobians and Hessians
205(1)
Concerning Jacobians
205(6)
Concerning Hessians
211(6)
Some Examples of Matrix Calculus Derivatives
217(1)
Derivative of Element-Wise Operations
217(1)
Derivative of the Activation Function
218(2)
Summary
220(1)
9 Data Flow In Neural Networks
221(22)
Representing Data
222(1)
Traditional Neural Networks
222(1)
Deep Convolutional Networks
223(2)
Data Flow in Traditional Neural Networks
225(4)
Data Flow in Convolutional Neural Networks
229(1)
Convolution
229(5)
Convolutional Layers
234(3)
Pooling Layers
237(2)
Fully Connected Layers
239(1)
Data Flow Through a Convolutional Neural Network
239(3)
Summary
242(1)
10 Backpropagation
243(28)
What Is Backpropagation?
244(1)
Backpropagation by Hand
245(1)
Calculating the Partial Derivatives
246(3)
Translating into Python
249(4)
Training and Testing the Model
253(1)
Backpropagation for Fully Connected Networks
254(1)
Backpropagating the Error
255(3)
Calculating Partial Derivatives of the Weights and Biases
258(2)
A Python Implementation
260(4)
Using the Implementation
264(3)
Computational Graphs
267(2)
Summary
269(2)
11 Gradient Descent
271(32)
The Basic Idea
272(1)
Gradient Descent in One Dimension
272(4)
Gradient Descent in Two Dimensions
276(6)
Stochastic Gradient Descent
282(2)
Momentum
284(1)
What Is Momentum?
284(1)
Momentum in 1D
285(2)
Momentum in 2D
287(2)
Training Models with Momentum
289(5)
Nesterov Momentum
294(3)
Adaptive Gradient Descent
297(1)
RMSprop
297(2)
Adagrad and Adadelta
299(1)
Adam
300(1)
Some Thoughts About Optimizers
301(2)
Summary
303(1)
Epilogue 303(2)
Appendix: Going Further 305(1)
Probability and Statistics 305(1)
Linear Algebra 306(1)
Calculus 306(1)
Deep Learning 307(2)
Index 309
Ronald T. Kneusel earned a PhD in machine learning from the University of Colorado, Boulder. He has over 20 years of machine learning industry experience. Kneusel is also the author of Numbers and Computers (2nd ed., Springer 2017), Random Numbers and Computers (Springer 2018), and Practical Deep Learning: A Python-Based Introduction (No Starch Press 2021).