Teaching Fundamentals of Neural Networks with MATLAB

Overview

In this webinar attendees will explore how to utilize ‘Fundamentals of Neural Networks’ courseware. This material was developed by Prof. Potočnik in collaboration with the MathWorks Academia Team.

AI is generally recognized as a key technology broadly adopted in many application domains. Recently, the permeation of AI in different science disciplines has become predominant. Many universities started to design new courses aimed at teaching young students the fundamental theory of AI (e.g., neural network) so that students can effectively address the main challenges when entering the job market and/or contributing to research advancements. The material developed in this project is aimed at addressing the need from instructors to have ready-to-use content to teach the fundamental theory of AI. The content exploits the latest MathWorks teaching tools (e.g., online trainings, dedicated Toolboxes, Apps, and the online tools of the CWL) which can be used to explain the basics of AI and allow a quick understanding of AI with low-code solutions.

This teaching package contains modular contents for the introduction of the fundamentals of Neural Networks. The package consists of a series of MATLAB Live Scripts with complementary PowerPoint presentations. The package is intended to gradually guide the students toward basic concepts in neural networks through general demonstrations applicable to every field, spanning from science to engineering. The materials also include a classical engineering problem, namely industrial diagnostics of compressor connection rod defects.

The contents are mainly addressed towards undergraduate courses. However, the modular structure allows further integration within other (postgraduate) AI-based courses. Course application areas include Neural Networks, Deep Learning, Machine Learning, Industrial diagnostics and Condition Monitoring, and Autonomous Systems.

Highlights

• Introduction to Neuron Models, Architectures, and Learning
  
• Perceptron and ADALINE
• Backpropagation
• Dynamic Networks
• Radial Basis Function Networks
• Self-organizational maps
• Practical consideration
• Modular courseware
• Integration with Online Trainings in MATLAB Academy

About the Presenter

Primož Potočnik is an Assistant Professor at the University of Ljubljana, Faculty of Mechanical Engineering, Laboratory of Synergetics. Primož has expertise in neural networks and machine learning and has been collaborating on many industrial projects in the field of industrial condition monitoring and forecasting applications for the energy market. Additionally, he is teaching the courses Neural Networks, Autonomous Vessels, and Empirical modeling and characterization of processes at the University of Ljubljana. His bibliography is available on COBISS and ResearchGate.