(1/4) Taking a break from Twitter-break to post this PSA for #NLP twitter.
Thanks to recent work by @ryandcotterell 's group, Uniform Information Density hypothesis is back in vogue. Hailing from Info-theory background, I've heard variants of this idea & decided to dig up
(2/4) The search took me through the iconoclastic work of Ramon Ferrer-i-Cancho & finally landed me at "Konstanz im Kurzzeitgedächtnis - Konstanz im sprachlichen Informationsfluß?" published in 1980 by Gertraud Fenk-Oczlon. Upon writing to her, this is the reply I received ...
(1/10) Neural Structured Learning- Tensorflow👊
[ Graphs aided Classification ]
Shameless 🔌 : My doctoral work was in this very domain: kilthub.cmu.edu/articles/thesi…
(2/10) Kymatio:Wavelet scattering in Python✌️
Psst: A lot of the easy datasets (read the x-mnist family / cats-v-dogs / Hot-Dog classification) require NO backprop/SGD training histrionics. Wavelet filters FTW!
Credits: @FlatironCCM , @meickenberg , @ebelilov , @lostanlen et al