Deep learning and AI Application | MSc in Electronics and Technology

Course overview

The aim of this course focuses on machine learning models and several key steps of deep learning in the design and performance analysis of the major parts of deep neural network. This course covers image data preprocessing, convolutional neural networks, pooling, activation function design and selection, network construction and training, and analysis of training results.

What you will learn

Analyze and understand the basic knowledge in the field of artificial intelligence
Design networks for specific applications, process data, train and optimize networks
Evaluate and assess the performance of proposed solutions related to Object classification and detection
Construct the engineering needs of artificial intelligence systems with MATLAB or Python

Meet your instructor

Mian Pan

Course content

Session 1: Overview of Machine Learning Framework and Steps
Session 2: Principles and Implementation of Classical Machine Learning Algorithms
Session 3: Machine Learning (ML) Strategies
Session 4: Convolutional Neural Network
Session 5: Convolutional Neural Networks – Programming Practice
Session 6: Basic Algorithms of Deep Learning
Session 7: Deep Convolutional Neural Networks
Session 8: Deep Convolutional Neural Networks– Programming Practice
Session 9: The Object Detection Based on Deep Learning Neural Networks
Session 10: Design and Implementation of the Object Detection Based on Deep Learning Neural Networks Based on Matlab Platform
Session 11: Network Design and Implementation
Session 12: Programming for the Design and Implementation of the Object Detection
Session 13: final project design and field Report

Teaching methodology

Assessment

Assignments (40%) Written assignments throughout the course.
Final examination （60%） Will include combination of numerical exercises and open-ended theoretical questions.