Message boards :
News :
[TWIM Notes] Jan 5 2021 -- A 6 Month Retrospective
Message board moderation
Author | Message |
---|---|
Send message Joined: 30 Jun 20 Posts: 351 Credit: 7,657,933 RAC: 77,314 ![]() ![]() ![]() ![]() ![]() |
This Week in [email protected] Notes for Jan 5 2021 A weekly summary of news and notes for [email protected] Summary Happy 2021! This past week marked the 6 month anniversary of this project, so we wanted to look back at how far we've come, assess what's gone well, find areas we need to improve, and talk about the future. Overall, the community response has been amazing and we feel like we've built a really solid foundation for understanding and evaluating neural networks. We'll list some of our thoughts below, and we encourage you, the community to comment below with your thoughts as well. The Good
|
Send message Joined: 11 Jul 20 Posts: 22 Credit: 520,875 RAC: 2,246 ![]() ![]() ![]() |
You're making a GREAT work!! |
Send message Joined: 4 Dec 20 Posts: 20 Credit: 12,243,579 RAC: 256,946 ![]() ![]() ![]() ![]() |
A One-Man-Show? Very brave to start this! I really hope that you will get help soon! Great work, really! |
Send message Joined: 4 Aug 20 Posts: 2 Credit: 219,018 RAC: 1,130 ![]() ![]() |
What are neural networks? What do they do? What is the purpose of creating them and what is it all for? |
![]() Send message Joined: 2 Jul 20 Posts: 7 Credit: 419,708 RAC: 4,834 ![]() ![]() ![]() |
Under Plans an Goals after your primary goals are implemented please consider adding a 32 bit application for Windows. There are a lot of older systems are still powered up looking for work, after Seti, on a Science related project. Run Time might be about 60 minutes. Bill F Dallas TX ![]() |
Send message Joined: 30 Jun 20 Posts: 351 Credit: 7,657,933 RAC: 77,314 ![]() ![]() ![]() ![]() ![]() |
@Bill F, I'm not sure that pytorch, our underlying library, supports 32 bit builds... but its definitely worth considering. And hand coding a neural network isn't hard per-se, but will get harder as we test more and more complex networks in the future. @David Mecha : to find out more about the project, please see the main website at https://www.mlcathome.org/, specifically the homepage, the MLDS Datasets page, and the FAQ. You can also get an introduction by listening to the BOINC Radio podcast for [email protected] available here: https://boinc.network/boinc-radio/mlchome/ , and browse the Science area of our forums. A lot of places link to the BOINC project page https://www.mlcathome.org/mlcathome/ , and many people miss the main site at https://www.mlcathome.org/. |
Send message Joined: 4 Aug 20 Posts: 2 Credit: 219,018 RAC: 1,130 ![]() ![]() |
Thank you. I think I understand it a little more now. |
Send message Joined: 4 Jul 20 Posts: 3 Credit: 1,051,960 RAC: 0 ![]() ![]() ![]() ![]() |
BRAVO for your commitment and courage, keep up the good job and community animation as you are doing, this is fundamental for a *good* boinc project :) I hope you'll find tech & admin & scientific help for your project, but I'm afraid this is the most difficult part of all, and I know that many boinc project died just because of this, the one-man-show turns out to be exhausting after some time. I wish you the best of luck with all this ! |
![]() Send message Joined: 4 Oct 20 Posts: 5 Credit: 189,542 RAC: 1,419 ![]() ![]() |
Great job! In which journal or journals do you plan to publish the papers? ![]() |
Send message Joined: 12 Jul 20 Posts: 33 Credit: 23,921,906 RAC: 229,406 ![]() ![]() ![]() ![]() ![]() |
I am glad that I am retired and don't have to do 1% of what you do. It makes the head spin just reading about it. But there are few projects where you can be in the top 1% (at the moment) with just two GTX 1060's on Ubuntu. I like efficiency, and the work matches well to the cards. |
New member Send message Joined: 8 Jan 21 Posts: 1 Credit: 0 RAC: 0 |
OK,DONE |
Send message Joined: 9 Jul 20 Posts: 105 Credit: 2,155,046 RAC: 27,754 ![]() ![]() ![]() ![]() ![]() |
Happy new year to you as well! Great read! Enjoyed the journey so far as a volunteer of this project. Most of all, the technical discussions on the forums about the science behind and the differences between the various experiments. Currently off to exploring Tensorflow/Keras for the first time myself, trying myself at my very first "big" data science projects doing NN-regressions. Model tuning (Hyperparameter) is such a labour-some job, …. Not coding whole applications, but rather just working with the Keras API for R. Still nice, seeing that the learning output of the stderr files of the WUs is oddly familiar! I'll happily bring back the GPUs in the meantime after testing. Overall, great progress! Good luck with your paper and looking forward to the new runs. |
Send message Joined: 22 Jul 20 Posts: 1 Credit: 59,172 RAC: 377 ![]() ![]() |
Happy 2021! I didn't know this was a one man project, wow. Hats off to you John for what this project has already accomplished in half a year. I am no scientist and glad to help a tiny little bit with the processing power in front of me. Thanks for shouting out the Discord and the BOINC radio, I didn't know about those. Here is to another awesome six months and hopefully more ML researchers being excited about collaborating with MLC. ![]() |
©2021 [email protected] Team
A project of the Cognition, Robotics, and Learning (CORAL) Lab at the University of Maryland, Baltimore County (UMBC)