See a map of all the places I've given a talk!
Workshop, SYSU, Singapore, SINGAPORE
This talk is about EEG-based emotion classification using a kernel attention module. The method is designed to work with limited EEG data, which is often a challenge in emotion recognition tasks.
Paper: đź“„KAM - A Kernel Attention Module for Emotion Classification with EEG Data
Code: GitHub Repository
Workshop, SYSU, Singapore, SINGAPORE
This talk is about EEG-based emotion classification using a monotonicity constrained attention module. The method is designed to work with limited EEG data, which is often a challenge in emotion recognition tasks.
Paper: đź“„A Monotonicity Constrained Attention Module for Emotion Classification with Limited EEG Data
Code: GitHub Repository
Workshop, SYSU, Guangzhou, CHINA
This talk is about proposing several points for improving qualitative analysis on deep learning based EEG emotion classification with noisy labels.
Workshop, University of Ottawa, ShenZhen, CHINA
This talk is about Deep Learning based Medical Image Registration with cycle-consistent loss.
Paper: đź“„Cycle-Consistent Training for Reducing Negative Jacobian Determinant in Deep Registration Networks
Code: GitHub Repository
Workshop, University of Ottawa, ShenZhen, CHINA
This talk is about Deep Learning based Medical Image Registration.
Paper: đź“„FAIM - A ConvNet Method for Unsupervised 3D Medical Image Registration Code: GitHub Repository
Talk, Banff, Banff, Alberta, Canada
Convnets, a different view of approximating diffeomorphisms in medical image registration. ▶️ Watch the Video
Talk, NRC, 1920 Research Private, Ottawa, Ontario, Canada
Some ideas for improving current Raman spectra matching algorithms presented in a industrial problems solving workshop held by NRC-CNRC and Fields Institute
Workshop, University of Ottawa, Ottawa, Ontario, Canada
This talk is about using neural networks for the task of medical image registration/alignment.
Talk, Chatham University, Pittsburgh, Pennsylvania, USA
This talk is about classifying different jet plane’s countour using extracted momenta features using a particle formulation.
Conference proceedings talk, Rocky Mountain Mathematics Consortium, 2016, Laramie, WY
Using posterier predictive distribution to find outliers in the data.