Don't miss the new Reading Group hosted by the Department of Computer Science of the University of Copenhagen on September 13, 2023.
SustainML is happy to announce the launch of a new initiative —a reading group to explore research papers linked to our project's topics, promoting collaboration and knowledge exchange within our community.
The first meeting is next Wednesday, and the paper Justification for Model Pruning will be presented. The study examines neural network compression, revealing the trade-off between compression and performance. The importance of pruning is emphasized, and compression introduces a successful pruning strategy, outperforming existing methods on CIFAR-10 and ImageNet datasets.
Key Details
Meeting Schedule: Every other Wednesday
Time: 15:30 - 16:30 (GMT/UTC)
Format: Each session will feature one person presenting a research paper and leading the ensuing discussion while others actively participate and engage in the conversation.
How to Get Involved
All are welcome to join and contribute to our project's intellectual growth. If you want to join, please send an email to Dusting Wright (This email address is being protected from spambots. You need JavaScript enabled to view it.) as described:
- Listening: If you want to join the reading group as a listener, you are more than welcome! Show up to the meetings and enjoy the discussions.
- email's subject to This email address is being protected from spambots. You need JavaScript enabled to view it.: “[Your Email Address] listen”
- Presenting: Let us know if you are eager to take the lead and give a paper relevant to our project in one of our upcoming sessions.
- email's subject to This email address is being protected from spambots. You need JavaScript enabled to view it.: “[Your Email Address] present”
Mark September 13 on your calendar, and don't miss the event!!
SustainML participants:
DFKI, Inria, IBM, University of Copenhagen, UpMem, Technische Universität Kaiserslautern, and eProsima.
More Information about SustainML:
For any questions, please get in touch with This email address is being protected from spambots. You need JavaScript enabled to view it..