Course Introduction
- Course Name: Convolutional Neural Network
- Course Code: CSH4R3
- Credits : 3
- Deep Learning on Neural Network
- Specific example on Computer Vision
Prerequisite: Basic Knowledge Required
- Proficiency in Algorithm and Programming
- Calculus, Linear Algebra
- Artificial Intelligence
Prerequisite: Equivalent knowledge
- Digital Image Processing
- Machine Learning
- Visual Recognition System
Course Objective
- Specific materials aimed to support your thesis
- Specific example on Computer Vision
- Understand and able to Implement Convolutional Neural Network
- Write from scratch, debug and train CNN
- Presenting the most recent research and developments around Neural Net and Deep Learning
- Current State of the Art Research
Points
- CLO 1 (40%) : ConvNet
- Identify and explain recent advancement and developments of Convolutional Neural Network
- CLO 2 (30%) : ConvNet API
- Implement Convolutional Neural Network API from scratch (forward and backward API)
- CLO 3 (30%) : ConvNet in Practice
- Apply ConvNet to a specific case
Point Distribution
| A | 80 … 100.0 |
| AB | 75 … 79.9 |
| B | 70 … 74.9 |
| BC | 60 … 69.9 |
| C | 50 … 59.9 |
| D | 40 … 49.9 |
| E | 0 … 39.9 |
Lecture Slides
- [tba]
Exercises
- 00 – NumPy Exercise
- [tba]
Class Exercises
- [tba]
Previous Class