A Gentle Introduction to Machine and Deep Learning (February 2020)

If you are curious about the big buzz around artificial intelligence (AI), machine learning and deep learning and want to get a real feel for how these technologies work, this bootcamp and hackathon will provide you with a hands-on introduction. These techniques allow one to build machines with near human performance in image classification, speech recognition, handwriting transcription, autonomous driving and drive digital assistants such as Google Now, Apple Siri and Amazon Alexa.

The course requires some basic exposure to computer programming using any programming language (e.g., Python, Visual Basic, C, JavaScript, etc.). This course is meant for the uninitiated who wish to explore pursuing a career in AI, machine learning, deep learning or data science, are contemplating a startup based on AI, or are just curious.

This is an interactive course and students will go through a series of hands-on exercises to apply the most successful recent techniques in machine learning and deep learning. After taking this course, you will have a broad overview of how to apply these technologies and the types of problems they can address. The course will be conducted in a state-of-the-art laboratory with the most recent machines pre-installed with all the tools and software you need. Just bring yourself.

Day 1

• Introduction to Machine Learning

• Supervised Learning

• Break

• Unsupervised Learning

Day 2

• Introduction to Deep Learning

• Break

• Hackathon

To regiser, please visit www.auscse.com/ai.

Presenter

Dr. Imran Zualkernan received a PhD in Computer Science with a concentration in Artificial Intelligence (AI) from the University of Minnesota, Minneapolis. He did his post-doctoral work in cognitive science at the Center for Research in Learning, Perception and Cognition. He published his first paper in AI in 1985. He has over 175 refereed publications and has published in applying AI and machine learning in VLSI fabrication, statistical experimental design, finance, smart homes, sports, transportation, emotion detection, smart retail spaces, sustainable energy and education analytics. He has developed an undergraduate course in deep learning (COE 494-12 Neural Networks and Deep Learning) and has developed and taught graduate courses (ESM 615 and COE 594-05) in machine learning and data analytics since 2015. He has also developed a PhD a course in big data analytics (ESM 733 Tools for Big Data). His coauthored paper on applying big data technologies in the context of smart homes recently received the IEEE Consumer Electronics Society’s Chester Sall Award for the first-place best paper in the IEEE Transactions on Consumer Electronics.

For more information or enquiries, please contact [email protected].