Yani Ioannou
Positions
Assistant Professor
Schulich School of Engineering, Department of Electrical and Software Engineering
Contact information
Phone number
Office: 403.220.6144
Location
Office: ICT248
For media enquiries, contact
Joe McFarland
Media Relations and Communications Specialist
Cell: +1.403.671.2710
Email: Joe.Mcfarland@ucalgary.ca
Preferred method of communication
How to Contact Me:
Undergraduate/Graduate Research Opportunities
Please see my supervisor profile for details on how to apply for these opportunities.
Research Collaborations
For research collaborations, please e-mail me directly.
I'm looking for...
Research partners
I have a wide-range of industry and academic research experience, and am always open to new collaborations, especially on projects which might help fund M.Sc. and PhD students (e.g. MITACs funding)
Background
Educational Background
PhD Information Engineering, University of Cambridge, 2018
M.Sc. Computing, Queen's University (Kingston, Canada), 2010
B.Sc. Honours Computer Science, University of Toronto, 2006
Biography
I completed my PhD at the University of Cambridge in 2018, where I was supervised by Professor Roberto Cipolla and Dr. Antonio Criminisi. My PhD was supported by a Microsoft Research Ph.D. Scholarship and I collaborated with researchers at Microsoft Research Cambridge (UK) extensively. Following my PhD I was a Postdoctoral Research Fellow at the Vector Institute, working with Prof. Graham Taylor, and Prof. Mihai Nica, and before that a Visiting Researcher at Google Brain Toronto/AR Core.
Research Impact
In my PhD I made research contributions in structured sparsity for Convolutional Neural Networks (CNNs) that are now widely used in all modern deep learning architectures for computer vision. I also worked on pioneering work in understanding the difficulty of adversarial robustness, and some of the earliest work applying CNNs to brain tumour segmentation. More recently I worked with NASA/SETI on applying deep learning to exoplanet classification, the resulting method continues to be used in processing data from the Transiting Exoplanet Survey Satellite (TESS) space telescope.
Current Research Interests
My current research focus is on unstructured sparse training of deep neural networks, and efficient deep learning more generally, with a focus on problems in computer vision in particular.
Industrial Research Experience
Outside of academia, I have a range of industrial research experience, including at Microsoft Research Cambridge (Intern/Business Guest), Google Brain Toronto (Visiting Resarcher), and a UK self-driving startup Wayve (Research Scientist). Outside of research, I've contributed to open source projects such as the Linux kernel and the Point Cloud Library (PCL).
Research
Areas of Research
My current research focus is on unstructured sparse training of deep neural networks, and efficient deep learning more generally, with a focus on problems in computer vision in particular.
I have worked on many computer vision applications such as conditional imitation learning for self-driving vehicles, medical imaging (brain tumour segmentation), 3D computer vision (point cloud segmentation), assistive technology (fall detection).
Participation in university strategic initiatives
Courses
| Course number | Course title | Semester |
|---|---|---|
| SENG 401 | Software Architecture | Winter 2022, Winter 2023, Winter 2024 |
| ENSF 444 | Machine Learning | Winter 2024 |
Projects
In work featured at Google Cloud Next `19, published in Astrophysics Journal Letters and Astronomy & Astrophysics, I along with Dr. Michele Sasdelli mentored two planetary scientists, Dr. Megan Ansdell and Dr. Hugh Osborn in deep learning and computer vision towards improving methods to find exoplanets in data from the NASA Kepler and TESS missions
Awards
- Outstanding Reviewer, Asian Conference on Computer Vision (ACCV). 2020
- Student Travel Award, NeurIPS. 2016
- Student Travel Award, International Conference on Learning Representations (ICLR). 2016
- Student Travel Award, Microsoft Research. 2016
- Microsoft Research PhD Scholarship, Microsoft Research. 2013
- Amazon Research Award, Amazon. 2021
- Early Career Research Excellence Award, Schulich School of Engineering - Electrical & Software awarded. 2023
Publications
- Gradient Flow in Sparse Neural Networks and how Lottery Tickets Win. Utku Evci, Yani A Ioannou, Cem Keskin, Yann Dauphin. AAAI 2022. (2022)
- Rapid Classification of TESS Planet Candidates with Convolutional Neural Networks. Hugh P Osborn, Megan Ansdell, Yani Ioannou, Michele Sasdelli, Daniel Angerhausen, Douglas A Caldwell, Jon M Jenkins, Chedy Räissi, Jeffrey C Smith. Astronomy & Astrophysics. (2020)
- Scientific Domain Knowledge improves Exoplanet Transit Classification with Deep Learning. Megan Ansdell, Yani Ioannou, Hugh P Osborn, Michele Sasdelli, Jeffrey C Smith, Douglas Caldwell, Jon M Jenkins, Chedy Räissi, Daniel Angerhausen. The Astrophysical Journal Letters. (2018)
- Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups. Yani Ioannou, Duncan Robertson, Roberto Cipolla, Antonio Criminisi. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, Honolulu, Hawaii. (2017)
- Training CNNs with Low-Rank Filters for Efficient Image Classification. Yani Ioannou, Duncan Robertson, Jamie Shotton, Roberto Cipolla, Antonio Criminisi. International Conference on Learning Representations 2016 (ICLR), San Juan, Puerto Rico. (2016)
- Measuring Neural Net Robustness with Constraints. Osbert Bastani, Yani Ioannou, Leonidas Lampropoulos, Dimitrios Vytiniotis, Aditya Nori, Antonio Criminisi. Neural Information Processing Systems (NIPS) 2016, Barcelona, Spain. (2016)
More Information
For an up to date and full list of publications, see my Google Scholar Profile
Are you the profile owner?
Login to edit.