Courses Detail Information

VE581 – Convolutional Neural Networks for Visual Recognition

Instructors:

Credits: 3 credits

Pre-requisites: Vv214/Vv417, Vv216/256/286, Ve281

Description:

Computer vision has played an important role in many applications such as in search, image understanding,
mapping, medicine, drones, and self-driving cars. For those applications, visual recognition is the key task.
Recently, deep learning (neural network) technique has advanced the performance of these state-of-the-art
visual recognition systems. This course will cover selected core topics on computer vision and deep learning,
such as image classification, localization, and detection with convolutional neural network. Students will learn
to design their own neural networks to solve real-world problems, for example, medical imaging diagnosis.
Through this course, students are expected to gain both theoretical and practical skills in computer vision and
deep learning.

Course Topics:

Introduct1on
Math Basics
Machine Learning Basics
Image Classification
Loss Function and OptimizationIntroduction to Neural NetworksConvolutional Neural NetworksDeep Learning Tools
Deep Learning Tools
Guest Lecture
Train Convolutional Neural Networks
Train Convolutional Neural Networks
CNN Architectures
Project Proposal Presentation
Recurrent Neural Networks
Detection and Segmentation
Medical Imaging