Machine learning is transforming a variety of industries. The advent of big data is fuelling machine learning to new heights. In recent times, the sub-field of deep learning has gained huge popularity and has revolutionised machine learning. The purpose of this lecture is to take participants through the journey from machine learning to deep learning using a systems approach. Case studies and examples will be given to reinforce understanding.
Who Should attend
This webinar is intended as an introduction for engineers and scientists who want to gain a foundational understanding of machine learning and deep learning. Participants will be introduced to concepts in machine learning, artificial neural networks and statistics and its evolution to solving larger problems through deep learning.
- Define key aspects of machine learning
- Understand how machine learning and statistics relate to each other
- Understand artificial neural network models
- Understand the four categories of machine learning algorithms
- Describe problems that require machine learning, statistical and deep learning approaches
- Explore the benefits of deep learning
- Understand key challenges and limitations of machine learning and deep learning
Dr. Bala Amavasai is currently Senior Scientist at Procter & Gamble’s R&D laboratory in Reading, UK. He specialises in data science, imaging and sensors. Prior to this, from 1999-2008, he was Head of the Mobile Machines and Vision group at Sheffield Hallam University, UK. He has vast experience in leading and working in European and UK collaborative research programmes.
In 2007, he was awarded the Outstanding Contributions Award by the IEEE Systems, Man and Cybernetics Society (SMC) and in 2017 he was awarded the exemplary service award by the IEEE UK & Ireland Section. He received both his B.Eng (Electronics Engineering) and Ph.D. (Machine Learning) degrees in the 1990s from the University of Sheffield, UK. He currently serves as Vice-Chair for the IEEE SMC in the UK and Ireland.
This Webinar is accredited by IEEE UK and Ireland Section