Dear all,

Please see the following notice from IEEE student branch from University of Guelph. All are welcome! 

---

Join the IEEE Student Branch and the University of Guelph’s School of Engineering for networking and research talks.  Learn about advances in medicine and machine learning from invited speakers, Dr. April Khademi and Dr. Graham Taylor as we aim to answer the question "Can Advances in Computing Replace Human-based Analysis?"

Gain knowledge about the cutting edge research being conducted at UoG!  See attached poster and below for more details.

Please register here: https://goo.gl/JPFI0Z

Location: University of Guelph, Atrium in the Thornbrough Building, http://www.uoguelph.ca/campus/map/thornbrough/

March 24, 2016

5:00pm - Networking & Refreshments

5:30pm - Intro to IEEE

5:45pm - Presentations

6:45pm - Q&A, Networking

SPEAKER INFORMATION:

Title: Disease Quantification Strategies for Radiology and Pathology Images

Speaker: April Khademi

Abstract: At the Image Analysis in Medicine Lab (IAMLAB), we are designing algorithms that extract insights from medical images, to help radiologists and pathologists quantify disease in a new way.  In particular, we are developing image processing tools that extract quantitative biomarkers from medical images, and data fusion strategies that integrate these imaging features with non-imaging clinical data for disease modeling and outcome analysis.   In this brief overview, we will explore some of the novel algorithms developed to investigate disease causation and progression for neurological disease (MRI) and breast cancer (digital pathology).  Image processing methods such as artifact modeling, preprocessing, segmentation, feature extraction and classification will be highlighted, alongside the promise of data fusion and integration strategies for personalized disease analysis.

Biography: Dr. April Khademi is Assistant Professor of Biomedical Engineering at the University of Guelph, and Director of the Image Analysis in Medicine Lab (IAMLAB), which specializes in the design of algorithms for Pathology and Radiology images, as well as for clinical bigdata.  The algorithms are applied to breast cancer and neurodegenerative (stroke, multiple sclerosis, Alzheimer’s) diseases. Her research has resulted in high impact journal publications, patent disclosures, invited talks and an NSERC Discovery Grant.  She currently serves as Associate Editor for IEEE (CJECE and Canadian Conference Board) and is on the Scientific Committee of the European Congress of Digital Pathology.  April holds a Ph.D. degree in Electrical Engineering from the University of Toronto and has had previous roles in research at GE Healthcare, PathCore Inc., Sunnybrook Research Institute and Toronto Rehab Institute. Her research and academic excellence has been acknowledged through several awards: Governor General Gold Medal, NSERC CGSD, L’Oréal UNESCO for Women in Science and Google Anita Borg Scholar.

Title: Deep Learning – Challenges and Opportunities

Speaker: Graham Taylor

Abstract: A central challenge in data analysis is that of untangling the many factors of variation that explain observations, for example, images, video, sound, or text, into useful features that can turned into useful outputs such as visualizations or decisions. To date, the dominant methodology for addressing this challenge has been to engineer a feature extraction pipeline, usually containing multiple stages of processing. An alternative approach is "Representation Learning": relying on the data, instead of feature engineering to learn representations that are invariant to nuisance factors. Techniques that learn multiple layers of representation, which are referred to as "Deep Learning", have demonstrated not only impressive success in recent benchmarks and competitions but applicability to multiple domains.  In this brief overview, I will review the foundations of Deep Learning and highlight the challenges the field brings to technical computing and the opportunities that may be afforded by parallelization and hardware acceleration.

Biography: Dr. Graham Taylor received his PhD in Computer Science from the University of Toronto in 2009, where he was advised by Geoffrey Hinton and Sam Roweis. He spent two years as a postdoc at the Courant Institute of Mathematical Sciences, New York University working with Chris Bregler, Rob Fergus, and Yann LeCun. In 2012, he joined the School of Engineering at the University of Guelph as an Assistant Professor. His research focuses on statistical machine learning, with an emphasis on deep learning and sequential data. He has applied his research to problems in computer vision, graphics, weather modeling, and finance, leading a number of academic-industry collaborations. Computing is at the heart of Dr. Taylor's research. As one of the first adopters and advocates of general-purpose GPU computing at the University of Toronto and New York University, Dr. Taylor introduced new opportunities for empirical investigation of machine learning algorithms. The result was a major investment of high-performance computing (HPC) infrastructure at both institutions, which has revolutionized the way empirical machine learning research is conducted.