Excited at #SIGMOD2018, where @tim_kraska just presented our paper on Learned Indexes after debate from research community. Paper was updated recently w/ appendices that address comments over the past several months, including alternative hashmaps. https://t.co/9prgOGe1bc https://t.co/aWx9wYEtnZ
— Ed H. Chi (@edchi) June 12, 2018
The Dockerized @PyTorch implementation of our @acl2018 paper Global-Locally Self-Attentive Dialogue State Tracker (https://t.co/WGMKyZwPPK) is now available on Github (https://t.co/4D0Iry2F5i). #nlproc
— Victor Zhong (@hllo_wrld) June 12, 2018
ConvNet outperforms human dermatologists for melanoma detection.
— Yann LeCun (@ylecun) June 12, 2018
Dermatologists in level-II protocol:
- sensitivity: 88.9% (±9.6%, P = 0.19)
- specificity: 75.7% (±11.7%, P < 0.05).... https://t.co/L3kmXgQufa
AI could get 100 times more energy-efficient with IBM’s new artificial synapses https://t.co/sMYPhCfeJF
— MIT Tech Review (@techreview) June 12, 2018
Backdrop: Stochastic Backpropagation
— ML Review (@ml_review) June 12, 2018
By @KyleCranmer
Intuitively: a dropout acting only along the backpropagation pipeline, that significantly improve generalization.https://t.co/avByBt9CSA pic.twitter.com/vPwI3HW4nY
New paper: "Reconstructing networks with unknown and heterogeneous errors"https://t.co/nGfIHZngVK
— Tiago Peixoto (@tiagopeixoto) June 12, 2018
Did you know you can make error estimates from networks, by making only a single measurement? pic.twitter.com/1yeYLC93Vn
Code, pre-trained models and paper: "QuaterNet: A Quaternion-based Recurrent Model for Human Motion" by Dario Pavllo, David Grangier and Michael Auli.
— Yann LeCun (@ylecun) June 12, 2018
Code: https://t.co/8pEGUAKNeZ
Paper: https://t.co/YA5etbCJdW https://t.co/J9MZ3NvyTE
Looking for a piece about autonomous weapon systems that manages to link Shakespeare, war dogs, and swarming drones? Looks no further - "Autonomous Weapon Systems and the Limits of Analogy" was published today!https://t.co/zfMqKIypeL
— R-Croo-D2 (@RebeccaCrootof) June 11, 2018
Very interesting paper that uses the Frobenius norm of the difference of the trained weights and their init in a Rademacher complexity bound. Can explain the counter intuitive improved generalization of wider nets. https://t.co/vWWh3M4lit
— Olivier Grisel (@ogrisel) June 11, 2018
"A Simple Method for Commonsense Reasoning," Trinh and Le: https://t.co/NnfE3HgwZb
— Miles Brundage (@Miles_Brundage) June 11, 2018
Language models used to improve performance on Winograd Schemas, etc. (still far short of human performance)
The code for our recent work, "Imitating Latent Policies from Observation," is now on github! @him_sahni @yscrcrhttps://t.co/u2xeA5rJP5
— Ashley Edwards (@RealAshEdwards) June 11, 2018
Whenever I criticize professors I get email from fellow profs admonishing me. Today it was the charge that I was "...attacking the people who have power, rather than diplomatically trying to change their minds".
— Chris Chambers (@chrisdc77) June 10, 2018
Dear Profs: This thread is my autoreply & my only reply. /1 https://t.co/NyD4pCdyzs
