This Book >>

  • 93pp. Published August 2018
  • Scientific Research Publishing,Inc.,USA
  • Category: Physics & Mathematics
  • ISBN: 978-1-61896-543-1
  • (Paperback) USD 69.00
  • ISBN: 978-1-61896-544-8
  • (E-Book) USD 29.00

Connect with SCIRP >>

Contact Us >>

Home > Books > Introduction to Mathematics for Understa...
Introduction to Mathematics for Understanding Deep Learning
  • Description
  • E-Book
  • Author(s) Information
Deep Learning is the heart of Artificial Intelligence and will become a most important field in Data Science in the near future. Deep Learning has attracted much attention recently. 
It is usually carried out by the gradient descent method, which is not always easy to understand for beginners. 
When one starts studying Deep Learning first hurdles are
(1) how to choose the learning rate
(2) how to avoid being trapped by local minima
(3) what is a deep meaning of the minibatch.
In this book I plan to offer intuitive answers to these questions within my understandings. 
As a matter of course, when beginners study Deep Learning some mathematical knowledge from Calculus, Linear Algebra, Statistics and Information are required. In the book I gave minimum knowledge required for understanding Deep learning.
After reading the book, readers are encouraged to challenge advanced books of Deep Learning (or Artificial Intelligence).
Components of the Book:
  • FRONT MATTER
    • Head Page
    • Copyright
    • Content
  • Chapter 1 INTRODUCTION
  • Chapter 2 FROM CALCULUS
    • 2.1. Calculus of Composite Functions
    • 2.2. Sigmoid Function
    • 2.3. Critical Point
    • 2.4. Gradient Descent Method
  • Chapter 3 FROM LINEAR ALGEBRA
    • 3.1. Vector Space and Matrices
    • 3.2. Eigenvalues and Eigenstates
    • 3.3. How to Estimate Eigenvalues
  • Chapter 4 FROM STATISTICS
    • 4.1. Elementary Knowledge
    • 4.2. Least Squares Method
  • Chapter 5 INFORMATION RETRIEVAL
    • 5.1. Vector Space Model of Information Retrieval
    • 5.2. Singular Value Decomposition of Matrix
    • 5.3. Singular Value Decomposition of Matrix: Example
  • Chapter 6 SIMPLE NEURON MODEL
    • 6.1. Logic Gate and Simple Neuron Model
    • 6.2. Least Squares Method and Simple Neuron Model
    • 6.3. Generalization of 6.2
  • Chapter 7 DEEP LEARNING
    • 7.1. Simple Neuron Model of Learning
    • 7.2. Deep Neural Network Model of Learning
    • 7.3. Minibatch of Deep Learning
  • Chapter 8 QUANTUM INTELLIGENCE: FUTURE TASK
    • 8.1. Quantum Mechanics
    • 8.2. Quantum Computation
    • 8.3. What Is Quantum Intelligence?
  • Chapter 9 CONCLUDING REMARKS
  • REFERENCES
Readership: People who like Mathematics, Computer and Artificial Intelligence, and school teachers
comments powered by Disqus