You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
1/ #DeepLearning is only good at interpolation. But applications need extrapolation that can reason about more complex scenarios than it is trained on. With current methods, accuracy degrades rapidly when complexity of test instances grows. Our new work aims to overcome this
2/We show that augmenting recursive networks with external memory like stack significantly improves extrapolation to harder examples. @ForoughArabsha1 @sameer_ Zhichu Lu
https://arxiv.org/abs/1911.01545 pic.twitter.com/48P14SIkbU
Interesting, would be nice to try that in connection to this physics task where we use tree recursive networks. https://arxiv.org/abs/1702.00748
Indeed! I had discussed with @cosmo_shirley about using recursive networks for physics problems. That is the right direction. Would be great to see how much external memory helps and how do we share stack parameters among different functions.
Thank you for this! Very cool! Have you tried comparing this to HyperNets: https://blog.singularitynet.io/just-deep-is-too-flat-b3813e2242f1 … seems like both methods try to generalize the usability of Neural Nets. The code for HyperNets is linked to at the bottom of the article
What do you think about information maximization over this memory augmented? Borrowing ideas from: https://www.linkedin.com/posts/adrian-b-690b61101_really-interesting-work-done-at-facebookai-activity-6597933652405952512-ICN0 … Applied it on language models but I think that it could be extrapolated to other areas.
Exactly my thoughts
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
