[4eyes] Summary of ML discussion meeting

[Pradeep Sen]

Thank you, Peter, for your leadership on all this and your help with the ML discussion group.

I also wanted to announce that we are going to start a similar group focusing on 3D rendering (physically-based rendering, real-time rendering, appearance modeling, etc.) with Lingqi.  We currently plan to hold it on Thursdays at 10am.

I hope that most of the folks in my group working on rendering problems can attend, and again I extend the invitation to the general 4Eyes/MIRAGE Lab community to welcome whoever is interested in coming by.  

We’ll run it the same way as the ML discussion group, with a five minute “presentation” by a student to lay out their problem and proposed approach followed by  in depth brainstorming and discussion.

Look forward to seeing some of you there!

Best,

-Pradeep

---
Pradeep Sen
Associate Professor
UCSB MIRAGE Lab
Dept. of Electrical & Computer Engineering
University of California, Santa Barbara
Santa Barbara, CA 93106-9560

> On Apr 28, 2019, at 6:29 AM, Peter Zhe Fu <peterzhefu at gmail.com> wrote:
> 
> Hi all,
> 
>      Just would like to summarize a few links we mentioned during our ML discussion meeting last Friday. Feel free to add links that I missed :-D
> 
>      1) at the beginning of our meeting, we talked about that often we have to wait 10+ hours before getting feedback on whether our change to algorithms work. While we discussed about various tips, earlier this week, Andrej Karparhy posted 'A recipe for training neural networks' on his blog. He shared many useful tips for training neural networks. It can be found here: http://karpathy.github.io/2019/04/25/recipe/
> 
>      2) the theme of our meeting was Jedrzej's idea on random networks. Earlier this month, Kaimimng He posted on ArXiv 'Exploring Randomly Wired Neural Networks for Image Recognition'. The authors obtained competitive accuracy on ImageNet Benchmark with randomly wired graph networks. It can be found here: https://arxiv.org/abs/1904.01569
> 
>      Also, maybe some of you could not make it due to time conflicts. So far we have been holding this ML discussion meeting on Friday 10 am. Usually one of us give a 5 min introduction to our research problem and challenges. Then all of us would pitch in to brainstorm. It has been tremendously helpful in my point view. So you are welcome to join or let me know if you prefer a better timing so we can conduct a Doodle poll.
> 
>     Have a great Sunday ahead :-D
> 
> Thanks and best regards,
> Zhe Fu (Peter)
> _______________________________________________
> Ilab-users mailing list
> Ilab-users at lists.cs.ucsb.edu
> https://lists.cs.ucsb.edu/mailman/listinfo/ilab-users
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cs.ucsb.edu/pipermail/ilab-users/attachments/20190428/c4aea010/attachment.html>