Work recently published by our close collaborators Drs. mariana bento (she/her) and Richard Frayne! Deep Learning in Large and Multi-Site Structural Brain MR Imaging Datasets frontiersin.org/article/10.338…

Join us for our #AAAI2022 *Oral Presentation* of our paper on Sparse DNN training: "Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win" tomorrow (Feb 24) @ 10:30-11:45am PST! Poster at 8:45-10:30am/Feb 27 4:45-6:30pm. Work with utku, Yann N. Dauphin, Cem Keskin.

Key takeaways: - Initialization is important for older NNs: use sparsity aware init. - For modern NNs, init doesn't matter: improving gradient flow during training helps (i.e. RigL) - Lottery tickets work since they re-locate the pruning solutions.

I was happy to recently be informed my 2022 DG proposal was also awarded a NSERC / CRSNG and National Defence DND Discovery Grant Supplement — one of only 20 awarded nationally — to further support and accelerate research at Calgary ML Lab! #DiscoveryGrants #NSERCsupport #CdnSci

I’m excited to share that I’ve received an Amazon Research Award for my proposal "Addressing Catastrophic Forgetting with Dynamic Sparse Training" at Calgary ML Lab/U Calgary! Learn more about the program on the Amazon Science website: amzn.to/ara-fall-winte… #AmazonResearchAwards

"Dynamic Sparse Training with Structured Sparsity" (openreview.net/forum?id=kOBkx…) was accepted at ICLR 2024! DST methods learn state-of-the-art sparse masks, but accelerating DNNs with unstructured masks is difficult. SRigL learns structured masks, improving real-world CPU/GPU timings

Happy to share our work on Knowledge Distillation temperature🌡️ and fairness⚖️. Must-read for AI practitioners given the prevalence of distilled models! KD is crucial in deploying AI, e.g. limited hardware, real-time applications 🙏Sara Hooker Mike Lasby for feedback! Calgary ML Lab

Congratulations Mohammed Adnan on receiving the RBC Borealis Fellowship! Adnan is a PhD student in the Calgary ML Lab lab at Schulich Engineering/U Calgary, and Vector Institute, co-supervised by Rahul G. Krishnan.

For more details, check out our full paper … 👇🏼 🔗: neurips.cc/virtual/2024/1… Joint work w/ Mohammed Adnan, Ekansh Sharma, and Yani Ioannou from Vector Institute and U Calgary. Visit our poster session on Dec 14 at #NeurIPS2024! 👋🏻 Supported by: Calgary ML Lab (6/6)

Really excited to be presenting this work from my lab at the NeurIPS Conference 2024 UniReps workshop! 🎉 If you are at NeurIPS and interested in the Lottery Ticket Hypothesis/sparse training, don’t miss our poster on Sat Dec 14th, 3:45-5:00 PM 🖼️🤓 Calgary ML Lab Vector Institute

I'm proud that the Calgary ML Lab lab will have 6 different works being presented by 6 students across #NeurIPS2024, in workshops (UniReps, WiML, MusiML) and the main conference! 🎉 Hope to see you at our posters/talks 🤓, full schedule at calgaryml.com 🧵(1/4)

1/10 🧵 🔍Can weight symmetry provide insights into sparse training and the Lottery Ticket Hypothesis? 🧐We dive deep into this question in our latest paper, "Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry", accepted at #ICML2025

Calgary ML Lab will be at #ICML2025 in Vancouver🇨🇦 next week: our lab has 6 different works being presented by 5 students across both the main conference & 6 workshops! We are also recruiting fully-funded ML PhD/MSc students🧑‍🎓If attending, reach out to me on Whova app to meet 📅

No tricks, just treats from our ML team. 👻