Deep Learning and Application
林小姐,電話:2788 5800
 查詢    打印  



Deep Learning Technology is a cross-discipline of technology among Big Data Analytics, Statistics and Neuroscience Technology.

It simulates how a human brain learn “Knowledge” from the real world. Some eye-popping results have shown up in addressing longstanding artificial intelligence problems.

Course Description

This is a two-day course that will elaborate from the ground-up in practical ways. Starting from basic big data machine learning concept, statistics methodology, and practical programmes running, commercial deployment for project managers.

Through this course, it aims to provide participants with:

  • Understand how this technology help in Internet of Things Projects and work with big data infrastructure
  • Understanding State-of-the-art Big Data Artificial Intelligence Technology
  • Learn how deep learning algorithms improve the accuracies of traditional AI algorithms
  • Learn basic statistics used in Big Data
  • Learn basic machine learning methodology
  • How deep learning help in image recognition and object tracking, sentiment analysis and decision making such as Chess / “Go” game
  • Practical Experience in writing deep learning programmes


30-31 July 2020


09:30 – 17:00


total 12 training hours


Cantonese (English terms will be used where appropriate)

Course Fee – Approved RTTP

HK$1,600*  (Original price: HK$4,800)
* Maximum saving, with the final grant subjects to approval.
This course is an approved Reindustrialisation and Technology Training Programme (RTTP) with up to 2/3 course fee reimbursement upon successful applications. For details:


It is highly recommended that participants process basic programming knowledge (Python) and basic statistical knowledge

Course Content Description by topics

Basic Knowledge in Big Data Analytics

  • What is Big Data, Big Data Infrastructure and Big Data Analytics
  • Trend and History of Big Data
  • 4 Vs of Big Data
  • Examples of Machine Learning

Overview of Neural Networks

  • Applications Examples in such as Artificial Neural Network, Recurrent Neural Network, Long-Short-Term Memory Network
  • Removal of Feature Engineering
  • Supervised & Unsupervised Learning

Basic Working Principles of Neural

  • Network
  • Statistics Basics
  • Linear Regression
  • Logistic Regression
  • Multiplayer Perception
  • Training and Testing DataSets
  • Over-fitting & Regularization

Artificial Neural Network

  • Deep Convolutional Network
  • Over-fitting
  • Perceptron Model
  • Forward Propagation
  • Back Propagation
  • Error Optimization and Loss Function
  • Differentiation Chain Rule
  • Activation function & Non-linearity
  • Sigmoid, ReLu, tanh functions
  • Gradient descent
  • Momentum & Learning Rate
  • Vanishing Gradient Problem

RNN & LSTM Network

  • Basic Concepts of Recurrent Neural Network
  • Basic Concepts of Word2Vec
  • Basic Understanding in using RNN in Textual Analysis
  • Application Examples of Recurrent Neural Network and LSTM

In-Depth Case Studies

  • Deep Learning in Image Processing, Audio Recognition, Sentiment Analysis, Natural Language Processing and Chess Contest & Playing Games

Overview of Deep Learning

  • Big Data Technology and Deep Learning
  • Introduction to Machine Learning
  • Introduction to Artificial Intelligence
  • What is / Why Deep Learning
  • Explosive Emerging Trends in Machine Intelligence
  • Supervised and Unsupervised Learning
  • Blending with Neuroscience Technology
  • Key Enabler: Big Data and Mathematics
  • The Challenge of Explosive Computational Bottleneck, Big Data Storage and Analytics
  • Impact to the Smart City
  • Internet of Things Intelligence
  • Applications of Deep Learning

Convolutional Neural Network

  • Convolution Layer
  • Max & Avg Pooling Layer
  • Filtering and Max-Pooling
  • SoftMax
  • Dropout Technique and Over-fitting
  • Data Augmentation
  • Applications of Convolution Neural Network

Deep Q Learning & Reinforcement Learning

  • Basic Concept of Reinforcement Learning, Q Learning and Markov Decision Process
  • Use of Deep Learning in Q Learning
  • Bellman’s Equation
  • Concept of Value-Based and Policy-Based Learning
  • Understanding on the use of Reinforcement Learning in Robotic Control, Playing Chess and Self-Driving Car

Case Study – Integration of AI into Big Data Infrastructure

  • Typical Infrastructure on Big Data Architecture with AI capability
  • Python in Machine Learning
  • Practical Examples of Artificial Intelligence and Deep Learning

Python AI Examples

  • Python Examples in Spark and Tensorflow
  • Use of Python Spark for Data Preparation for AI Data Input
  • Python Tensor-flow Network Programming Examples

Course Outline

  1. Basic Knowledge in Big Data Analytics
  2. Overview of Deep Learning
  3. Overview of Neural Networks
  4. Basic Working Principles of Neural Network
  5. Artificial Neural Network
  6. Convolutional Neural Network
  7. RNN & LSTM Network
  8. Deep Q Learning & Reinforcement Learning
  9. Case Study – Integration of AI into Big Data Infrastructure
  10. In-Depth Case Studies
  11. Python AI Examples

Award of Certificate

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

Who Should Attend?

It is designed for project managers, software developers, and statisticians. It is an advanced extension to Internet of Things and Big Data Project. Project manager, who intends to utilize Big Data Intelligence into their projects, can learn what, why and how Deep Learning works in the project; Software developers and system integrators can learn practically how algorithms and software can be written.


Mr. LEE Chi Man, Alan graduated from the Chinese University of Hong Kong with a Master of Philosophy degree in Information Engineering and a Bachelor of Engineering degree in Information Engineering (with a First Class Honor). Before founding his company, Alan held senior management role in technology group and director position in investment bank. Alan Lee oversaw the corporate strategy, merger and acquisition, product development and production management. Prior to this, he served in investment bank and capital market on risks, production management, technology, research, analytics roles and high frequency technology positions.


Download Full Course Detail ▼