Businesses worldwide are using artificial intelligence (AI) to solve their greatest challenges. Healthcare professionals use AI to enable more accurate, faster diagnoses in patients. Retail businesses use it to offer personalized customer shopping experiences. Automakers use it to make personal vehicles, shared mobility, and delivery services safer and more efficient. Deep learning is a powerful AI approach that uses multi-layered artificial neural networks to deliver state-of-the-art accuracy in tasks such as object detection, speech recognition, and language translation. Using deep learning, computers can learn and recognize patterns from data considered too complex or subtle for expert-written software. In this workshop, you'll learn how deep learning works through hands-on exercises in computer vision and natural language processing. You'll train deep learning models from scratch, learning tools and tricks to achieve highly accurate results. You'll also learn to leverage freely available, state-of-the-art pre-trained models to save time and get your deep learning application up and running quickly. This workshop is a collaboration between NVIDIA, University of Regina, and Murdoch University.
The primary objective of this workshop is to provide an opportunity to researchers to deploy their deep learning algorithms on cloud-based
GPUs and train and test deep neural networks in real-time. In addition, attendees will learn how to build deep learning and accelerated
computing applications across various industry segments such as autonomous vehicles, digital content creation, finance, game development,
and healthcare.
At the conclusion of the workshop, attendees will understand the fundamentals of deep learning and be able to:
Research students, academics and developers from industry.
Abdul Bais received his B.Sc. and M.Sc. degrees in electrical engineering from the University of Engineering and Technology, Peshawar,
Pakistan, and a Ph.D. degree in electrical engineering and information technology from Vienna University of Technology Vienna, Austria. From
2010 to 2013, he was a postdoctoral fellow with the Faculty of Engineering and Applied Science, University of Regina, Saskatchewan, Canada.
He is currently an Associate Professor with the electronic systems engineering program at the Faculty of Engineering and Applied Science,
University of Regina, SK, Canada. His research interests include real-time data stream mining, deep learning/machine learning, image processing,
and computer vision. Abdul Bais's current research projects include multi-source data processing for precision agriculture, accent and language-based
speaker recognition for forensic applications, and detection of cohesive communities in multimedia images. His research is supported by The Natural
Sciences and Engineering Research Council of Canada (NSERC Alliance and Discovery programs), Mitacs (www.mitacs.ca), and the AgTech industry. He is a
certified instructor with the NVIDIA Deep Learning Institute (Fundamentals of Deep Learning and Fundamentals of Accelerated Data Science with RAPIDS).
He is a senior member of the IEEE and a Licensed Professional Engineer in Saskatchewan, Canada.
Syed Afaq Shah received the Ph.D. degree in computer vision and machine learning from The University of Western Australia (UWA), WA, Australia. He was a Lecturer ICT with Central Queensland University, QLD, Australia. He is currently a Lecturer with Murdoch University, Perth, WA, Australia. and Adjunct Senior Lecturer with the Department of Computer Science and Software Engineering, UWA, Perth, WA, Australia. His research interests include deep learning, robotics, 3-D object/face recognition, 3-D modeling, and image processing. He has published over 50 research articles in the area of machine learning and computer vision, and co-authored a book," A Guide to Convolutional Neural Networks for Computer Vision". His publications have received over 1000 citations. He was a recipient of the Start Something Prize for Research Impact through Enterprise for 3-D Facial Analysis Project funded by the Australian Research Council. He has been awarded over $200,000 in competitive internal and external research funding.
Please join MathWorks and learn how to get started with MATLAB for Deep Learning with Images. Come along to this hands-on-workshop to learn about the Deep Learning image classification workflow in MATLAB including image data management, network assembly, training, and experiment management. Create a Convolution Neural Network (CNN) from scratch programmatically and using Apps. Explore how to access and adjust pretrained models (transfer learning), and how to evaluate the network and improve its accuracy.
In this hands-on workshop, you will write code and use MATLAB Online to:
No installation of MATLAB is necesary. Please bring your laptop to the session.
Research students, academics and developers from industry.
Dr Emmanuel Blanchard is a senior application engineer at MathWorks who first joined the company as a training engineer in 2014. His main focus is on data analytics, which includes machine learning and deep learning. He taught several MATLAB and Simulink courses as well as specialized topics such as machine learning, statistics, optimization, image processing and parallel computing. Prior to joining MathWorks, he was a Lecturer in Mechatronic Engineering at the University of Wollongong. He holds a PhD in Mechanical Engineering from Virginia Tech. He also worked as a Systems / Controls Engineer at Cummins Engine Company and as a research assistant in several research institutions in California and Virginia
Deep learning has substantially influenced medical image analysis achieving unprecedented performance. This workshop aims to give hands on experience on how deep learning is being used, tailored, and specifically developed for medical imaging. We will demonstrate these with two case studies: Glaucoma detection from OCT scans using Python (by Dr Gorge) and COVID19 detection from X-ray and CT images using MATLAB (by Dr Islam).
Research students, academics and developers from industry.
Dr Yasmeen George is a research fellow with A2I2 at Deakin University with over a decade of research experience in AI healthcare analytics and data science. She received her Ph.D. from the University of Melbourne in 2018. She worked as associate lecturer and research fellow at the University of Melbourne, teaching data science related subjects and implementing AI-based solutions for event detection and social media analytics. Prior to joining Deakin, Yasmeen worked as research scientist with IBM Research Australia focusing on the use of AI for retinal disease diagnosis and patient monitoring, data analytics in health care, deep reinforcement learning and interpretability in machine learning. Yasmeen holds 3 patents for applications of AI in healthcare. Her research interests include AI, data science, healthcare analytics across domains of radiology, dermatology, and ophthalmology, biomedical informatics, and computer vision.
Dr Syed Islam completed his PhD with Distinction in Computer Engineering from the University of Western Australia (UWA) in 2011. He received his MSc in Computer Engineering from King Fahd University of Petroleum and Minerals in 2005 and BSc in Electrical and Electronic Engineering from Islamic Institute of Technology in 2000. He was a Research Assistant Professor at UWA (2011-2015), a Research Fellow at Curtin University (2013-2015) and a Lecturer at UWA (2015-2016) and Edith Cowan University (ECU) (2016-2020). Currently he is working as a Senior Lecturer in Computer Science at ECU. He has published over 60 scholarly articles, attracted 19 public media releases and received external grants of over a half a million dollars. He has supervised to completion of five HDR students and currently supervising eight others. He has been serving IEEE Access as an Associate Editor and Healthcare as a Guest Editor since 2020. He is also a regular reviewer of around 10 Q1 journals, Organising Committee member of seven conferences, Technical Committee member of 28 conferences and Senior member of both IEEE and Australian Computer Society. He is the Chair of Signal Processing Chapter and Educational Activities Coordinator of IEEE WA section. His research interests include (but not limited to) Artificial Intelligence, Machine Learning, Medical Imaging, Telerobotics and Computer Vision.