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
Hence DL is good for feature extraction/compression and beyond that tree like architectures should take over.
Is it applicable to algorithmic tasks? (Sort, addition, multiplication, etc, what NTM, Neural GPU and Universal Transformer did)
This tweet really downplays prior work. NTM, memory nets, Neural GPU, MANN, graph nets, and many, many other related methods also degrade gracefully. Your work looks like an important next step, but this rhetoric is unhelpful.
What you are doing is rhetoric and rude. We have mentioned all prior work in our paper. You don't want to engage in science.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
