Hopfield Networks is All You Need
— AK (@ak92501) August 6, 2020
pdf: https://t.co/SWFnVFNS8h
abs: https://t.co/erpgXRmPqJ
github: https://t.co/MWrtQlsNNO pic.twitter.com/0VmtHZK9QX
Hopfield Networks is All You Need
— AK (@ak92501) August 6, 2020
pdf: https://t.co/SWFnVFNS8h
abs: https://t.co/erpgXRmPqJ
github: https://t.co/MWrtQlsNNO pic.twitter.com/0VmtHZK9QX
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
— AK (@ak92501) August 6, 2020
pdf: https://t.co/KHINkovxPi
abs: https://t.co/XWSUJZeqMA
project page: https://t.co/7S682vbr18 pic.twitter.com/c3uH73XBJQ
New paper!
— Karl Rohe (@karlrohe) August 5, 2020
For the last century, we’ve misunderstood something fundamental about unsupervised learning.
This paper fixes it. 🧵https://t.co/Fnt94XUikS pic.twitter.com/7ReDLvedAP
arXiv: "The World as a Neural Network -- We discuss a possibility that the entire universe on its most fundamental level is a neural network."https://t.co/Py5o55Q9eE
— Delip Rao (@deliprao) August 5, 2020
Me: Yeah, and 2020 is the year of NaNs pic.twitter.com/iVflyqC5ZC
Fawkes: Protecting Privacy against Unauthorized Deep Learning Models
— hardmaru (@hardmaru) August 5, 2020
Add imperceptible pixel-level changes ("cloaks") to photos to fool face recognition models deployed by Microsoft, Amazon, Face++https://t.co/bIsro8D3iZ
Project page: Code, Mac/Win app https://t.co/WXu0QcFmUg pic.twitter.com/rW7Jjgl0Nm
"Bringing UMAP Closer to the Speed of Light with GPU Acceleration" -- as if @leland_mcinnes 's uniform manifold approximation& projection algorithm wasn't already fast enough, @cjnolet @datametrician et al now have a cuML version offering a 100x speedup :) https://t.co/KMwUOxrb41
— Sebastian Raschka (@rasbt) August 4, 2020
DeLighT: Very Deep and Light-weight Transformer
— AK (@ak92501) August 4, 2020
pdf: https://t.co/3BGksd53Bs
abs: https://t.co/QgKDzHmYy9
github: https://t.co/nZzapo7NCF pic.twitter.com/h0qsg58MRU
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
— AK (@ak92501) August 4, 2020
pdf: https://t.co/pAGNSvFSf9
abs: https://t.co/DpF5yJKz8d pic.twitter.com/OXCVyRWg8r
Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild
— AK (@ak92501) July 31, 2020
pdf: https://t.co/OH0auVxUaj
abs: https://t.co/DEysx6npIa pic.twitter.com/TTETeUMWKV
The need for open data & benchmarks in modern ML research has led to an outpouring of #NLProc data creation. But @harm_devries, @DBahdanau & I suggest the low ecological validity of most of this data undermines the resulting research. Comments welcome! https://t.co/scSc2c6Flq pic.twitter.com/9Lg8NJLxZT
— Christopher Manning (@chrmanning) July 30, 2020
Can supervised contrastive learning really outperform cross-entropy?
— Lavanya (@lavanyaai) July 30, 2020
In this report, @RisingSayak and Shweta introduce SCL and present a plethora of experiments to validate its efficiency.#machinelearning #deeplearning #100daysofmlcodehttps://t.co/D9YMZ8Uy5i
Just finished a trip down memory lane. Deep Learning's Most Important Ideas - A Brief Historical Review: https://t.co/XpBxi9xrCF
— Denny Britz (@dennybritz) July 29, 2020
If you want to get into Deep Learning research, these are what I consider the most important papers to start with!