Artificial Intelligence: Essentials & Application
 查詢    打印  


Course content

  • The first and most essential course in the whole AI series
  • Understand the state-of-the-art Big Data Artificial Intelligence Technology
  • Learn the principles of AI algorithms from the ground up, basic statistics and basic machine learning methodology
  • AI Technology including ANN, RNN, LSTM, DQN
  • Understand how deep learning help in image recognition, speech recognition, textual analytics, trend prediction, robotic control, self-driving, chess playing etc.

Who Should Attend?

  • For anyone who are interested in understanding the applications and principles of AI and strategy.
  • Project Manager & Management Executive, who intend to plan and utilize AI into their projects. They can learn what, why and how deep learning works in the project.
  • Software Developers and System integrators who can learn practically how algorithms and AI basics from the ground up.


Date : 23 & 24 April 2020 (Thursday & Friday)
Time: 09:30 – 17:00
Duration: 6 hours per day, total 12 lecture hours

Programme Structure

Chapter 1 : Introduction to Big Data Analytics

  • What is Big Data Infrastructure
  • What is Big Data Analytics
  • Trends & History
  • Big Data 4Vs
  • Framework
  • Concepts of Unstructured Data

Chapter 2 : Introduction to Artificial Intelligence

  • Introduction to AI & History
  • Examples in Deep Learning
  • AI Applications in Computer Visions
  • AI Applications in Face and Gesture Recognition
  • AI Applications in Object Detection
  • AI Applications in Activity Recognition
  • AI Applications in Image Generation
  • AI Applications in Robotic Controls
  • AI Natural Language Processing
  • GPU and Hardware in AI

Chapter 3 : Introduction to Deep Learning

  • Global Deep Learning Trends
  • Machine Learning Process
  • Supervised & Unsupervised Learning
  • Reinforcement Learning
  • Classification Application Type
  • Regression Application Type
  • Clustering Application Type
  • Error Rate & Accuracy
  • Concepts of Feature Engineering
  • Revolution of Depth Layers

Chapter 4 : From Regression

  • Machine Learning Basics
  • Training, Test & Validation Process
  • Over-fitting & Under-fitting
  • From the Ground Up: Regression
  • Linear Regression
  • Logistic Regression
  • Principles in Perceptron
  • Impact of Data Cleansing and Data Transformation
  • Impact of Feature Engineering

Chapter 5 : Neural Network Basics, ANN, CNN

  • Neural Network Basics
  • Neurons
  • Activation Functions
  • Optimization & Loss
  • Activation Functions
  • Neural Network Layers
  • Artificial Neural Networks
  • Principles in Gradient Descent
  • Neural Network Weight Update Mechanisms
  • Basic Structures in Artificial Neural Network
  • 2D & 3D Convolution Operation
  • Convolutional Neurons
  • Feature Maps
  • Convolution Neural Networks
  • Word2Vec Embedding

Chapter 6 : Recurrent Neural Basics (RNN, LSTM)

  • Introduction to Recurrent Neural Network
  • Unrolling RNN Cells
  • Gates in Memory Cells
  • Memory Concepts in AI Models
  • Long-Short-Term-Memory Cells
  • Why GPU Hardware is significant
  • Applications in Speech Recognition

Chapter 7 : Recurrent Neural Network in Text Analytics

  • Textual Feature Engineering
  • Features: TF-IDF, N-grams
  • Application in Handwritten Sequence Generation
  • Application in Reading Comprehension
  • Application in Part-of-Speech Recognition
  • Application in Text Summarization
  • Application in Co-reference Resolution
  • Application in Time Series Analysis
  • Applications in Textual Analytics
  • Brief Introduction to BERT Models for AI Text

Chapter 8 : Reinforcement Learning (DQN)

  • Concepts in Reinforcement Learning
  • Principles in Deep-Q-Learning
  • Applications in Robotic Control
  • Applications in Game-Strategy Playing
  • Applications in Chess Playing
  • Applications in Self-Driving Car

Course Fee


Programme Instructor

Mr LEE Chi Man, Alan
Mr Lee held a senior management role in the technology division of an investment bank, overseeing the corporate strategy, product development and production management for more than 14 years. With extensive IT background, Mr Lee possesses practical project experience on sophisticated analytics and large-scale global technology project management. He also has rich training experience in the design and delivery of Big Data analytics, Fintech and Blockchain Technologies and Applications.

Certificate & Award

Award prerequisites for “Diploma in Artificial Intelligence”:
1. Certificate Holder in related areas; or
2. Grade E or above in five subjects in HKCEE or equivalent; or
3. Five passes plus Level 2 or above in English and Chinese in HKCEE or equivalent; or
4. Level 2 in five subjects in HKDSE or equivalent: or
5. Mature student (Mature student for diploma courses must be 18 years old or above and with 2 years or above working experience)

Participants who complete a total 60 learning hours (any 5 workshops), with 75% attendance and pass the assessment will be awarded the “Diploma in Artificial Intelligence”
1. Artificial Intelligence : Essential and Application
2. Artificial Intelligence : Learning Keras
3. Artificial Intelligence : Data Science in Python
4. Artificial Intelligence : Programming in Tensorflow
5. Artificial Intelligence : Infrastructure Architect
6. Artificial Intelligence : Advanced Reinforcement Learning, Gan and Textual Analytic

Participants who have completed 100% attendance will be awarded a certificate of attendance issued by the Hong Kong Productivity Council.

Download Full Course Detail ▼