Moving away from standard parametric priors, our approach using non-parametric priors helps GANs counter distribution-mismatch problems. Just been accepted at the Intl. Conference on Machine Learning (ICML) 2019. Congrats to Rajhans Singh and team. Opens potentially new ways to enforce constraints on GAN outputs by designing priors more deliberately. Paper and code coming soon.
Author: pavanturaga
NSF travel awards for students working on topological methods
Happy to report that GML grad student Anirudh Som and visiting grad student Ankita Shukla (IIIT-Delhi), have both been selected to participate in the NSF-CBMS workshop on topological methods. Both have also received travel support to attend. Thank you NSF and CBMS. https://blogs.cofc.edu/cbms-tda2019/
Fulton top 5% teaching award
Humbled that I was selected to receive the Fulton School of Engineering’s Top 5% teaching award, to be presented in Fall 2019. I am grateful for the opportunity to teach many great undergrad and grad students, and also thank them for this honor.
Temporal Transformer Networks accepted at CVPR 2019
Paper by student Suhas Lohit and recent grad Qiao Wang on deep architectures for discriminative time-warps – a.k.a. Temporal Transformer Networks – accepted at CVPR 2019. Congrats!
IJCAI and Asilomar
Happy to be invited as Senior Program Committee Member for Intl. Joint Conf. on AI (IJCAI), and as track chair for speech-image-video at Asilomar 2019. Looking forward to help line up a strong and exciting program.
