HCIA-AI Training

الوصف

Course Description:

This course matches the HCIA-AI V1.0(Released on April 4,2019), Through the preparation for HCNA-AI, you will systematically understand and grasp Python programming, essential mathematics knowledge in AI, basic programming methods using Tensor Flow (a machine learning and Deep Learning platform framework), pre-knowledge and overview of Deep Learning, overview of Huawei cloud EI.

Objectives:

After completing these courses, you will be able to:

  • Understand the overview of AI.
  • Master the Python programming language.
  • Master the Math basics required for deep learning.
  • Understand the overview of the TensorFlow.
  • Understand the propaedeutics and overview of deep learning.
  • Understand the overview of Huawei cloud EI.
  • Know how to perform basic programming using Python.
  • Know how to perform mathematical programming using Python.
  • Know how to perform basic programming using TensorFlow.
  • Know how to perform basic programming for image recognition.
  • Know how to perform basic programming for speech recognition.
  • Know how to perform basic programming for man-machine dialogs.

Training Contents

Chapter 1 Overview of AI

  • l The Past, Present, and Future of AI
  • l Development of AI Industries
  • l Strategic Planning of AI in the World
  • l Justice and Equity in the Era of AI
  • l Man-Machine Relationship in the Era of AI
  • l AI Governance
  • l AI Society in the Future

Chapter 2 Python Programming Basics

  • l Introduction to Python
  • l List and Tuple
  • l String
  • l Dictionary
  • l Conditional and Loop Statements
  • l Function
  • l Object-Oriented Programming
  • l Date and Time
  • l Regular Expression
  • l File Manipulation

Chapter 3 Basic Math

  • l Linear Algebra
  • Special Matrices
  • Eigendecomposition
  • Singular Value Decomposition
  • Moore-Penrose Pseudoinverse
  • Trace Operator
  • Determinants
  • Example: Principal Component Analysis
  • l Probability and Information Theory
  • Random Variables
  • Probability Distribution
  • Marginal Probability
  • Conditional Probability
  • Independence and Conditional Independence
  • Expectation, Variance, and Covariance
  • Common Probability Distribution
  • Bayesian Rules
  • Continuous Variable
  • Information Theory
  • Structured Statistical Model
  • l Numeric Calculation
  • Overflow and Underflow
  • Ill-Condition
  • Gradient Based Optimization Method
  • Constraint Optimization
  • Example: Linear Least squares

Chapter 4 Introduction to TensorFlow

  • l What Is TensorFlow?
  • l TensorFlow Characteristics
  • l TensorFlow Basics
  • l TensorFlow Modules
  • l Development Environment Deployment
  • l Basic Development Steps Using TensorFlow
  • Defining the TensorFlow Input Node
  • Defining the Learning Parameter Variable
  • Defining the Operation
  • Optimizing Functions and Objectives
  • Initializing All Variables
  • Iterate and Update Parameters to the Optimal Solution
  • Testing the Model
  • Using the Model
  • l Other Deep Learning Frameworks

Chapter 5 Propaedeutics and Overview of Deep Learning

  • l Propaedeutics of Deep Learning
  • Learning Algorithms
  • Common Machine Learning Algorithms
  • Hyperparameter and Validation Set
  • Parameter Estimation
  • Maximum Likelihood Estimation
  • Bayes Estimation
  • l Overview of Deep Learning
  • Definition and Development of Neural Networks
  • Perceptron and Training Rules
  • Activation Functions
  • Types of Neural Networks
  • Regularization in Deep Learning
  • Optimizer
  • Applications of Deep Learning

Chapter 6 Huawei Cloud EI Overview

  • l Concept of AI and Origin of EI
  • l Details About Huawei Cloud EI
  • Basic Platform Services
  • Common Services
  • Industry-specific Services

Chapter 7 Python Programming Basics Experimental Guide

  • l List and Tuple
  • l String
  • l Dictionary
  • l Conditional and Loop Statements
  • l Function
  • l Object-Oriented Programming
  • l Date and Time
  • l Regular Expression
  • l File Manipulation

Chapter 8 Basic Math Experimental Guide

  • l Linear Algebra Practices
  • l Probability Theory Practices
  • l Numerical Computation Example Practices
  • l Scenario

Chapter 9 TensorFlow Programming Basics Experimental Guide

  • l Eight Knowledge Points
  • Hello World
  • Session
  • Matrix Multiplication
  • Definition of Variables
  • TensorBoard Visualization
  • Data Read and Processing
  • Graph Operation
  • Saving and Using Models
  • l Linear Regression — House Price Prediction

Chapter 10 Image Recognition Programming Experimental Guide

Chapter 11 Speech Recognition Programming Experimental Guide

Chapter 12 Man-Machine Dialogue Programming Experimental Guide