Very happy to share our latest work accepted at #ICRL2020: we prove that a Self-Attention layer can express any CNN layer. 1/5
— Jean-Baptiste Cordonnier (@jb_cordonnier) January 10, 2020
📄Paper: https://t.co/Cm61A3PWRA
🍿Interactive website : https://t.co/FTpThM3BQc
🖥Code: https://t.co/xSfmFCy0U2
📝Blog: https://t.co/3bp59RfAcj pic.twitter.com/X1rNS1JvPt
Looks useful: Keras-OCR (3rd-party package) provides out-of-the-box OCR models and an end-to-end training pipeline to build new OCR modelshttps://t.co/q7rN49VjvD
— François Chollet (@fchollet) January 4, 2020
"Today’s CNN-generated images (ex: #DeepFakes) retain detectable fingerprints that distinguish them from real photos. This allows forensic classifiers to generalize from one model to another without extensive adaptation."
— 👩💻 DynamicWebPaige (@DynamicWebPaige) December 24, 2019
📄: https://t.co/JVVp7EHFhp
💻: https://t.co/e70ZSTHiZ9 pic.twitter.com/h3UpcG00od
BackPACK: Packing more into backprop
— Thomas Lahore (@evolvingstuff) December 24, 2019
"we introduce BackPACK, an efficient framework built on top of PyTorch, that extends the backpropagation algorithm to extract additional information from first- and second-order derivatives"https://t.co/KzO1zq9eNahttps://t.co/ubtvZu1G5P pic.twitter.com/sX9Rp6We1w
A clean TensorFlow 2 implementation of StyleGAN 2 (with pretrained weights for generating landscapes) https://t.co/CT7RknBsQK pic.twitter.com/MuUQZ2mlfw
— François Chollet (@fchollet) December 16, 2019
PyTorch implementation of Neural Painters
— hardmaru (@hardmaru) December 14, 2019
Cool talk by @reiinakano at ML for creativity workshop. He released a new @PyTorch library and notebooks for others to easily play around with neural painter algorithms!https://t.co/XLgxSbndDshttps://t.co/hszDYqOJxt pic.twitter.com/Jcn5dG8PeF
Pretrained language models like quantized DistilBERT from @huggingface will launch a wave of creative AI applications running on mobile and embedded devices: https://t.co/ogYlzxYIIH
— Peter Skomoroch (@peteskomoroch) December 11, 2019
As promised, we have made the Text-To-Text Transfer Transformer (T5) models much easier to fine-tune for new tasks, and we just released a Colab notebook where you can try it yourself on a free TPU!
— Adam Roberts (@ada_rob) December 9, 2019
👇 https://t.co/l6eI88Ih3f
(1/3) pic.twitter.com/LU5scmhbIs
After a ton of work by a bunch of people, we're releasing an entirely new Neural Tangents.
— Sam Schoenholz (@sschoenholz) December 6, 2019
Paper: https://t.co/2KqBv44KJt
Github: https://t.co/iutzkEhEOM
Colab Notebook: https://t.co/JcxUkWwJ0h
We now have a distilled multi-lingual model in 🤗Transformers! https://t.co/xMRRNuwaZb
— Thomas Wolf (@Thom_Wolf) December 6, 2019
Another @kaggle competition @fastdotai v2 starter pack is here! 😄🥳🍾
— Radek Osmulski (@radekosmulski) December 1, 2019
In the repo so far:
✅downloading and processing data
✅training two basic models
✅averaging predictions and submitting to Kaggle!https://t.co/0m6BaNk2qT pic.twitter.com/tBu59pMuPX
We have released code to reproduce experiments in our paper “Learning to Predict Without Looking Ahead: World Models Without Forward Prediction” #NeurIPS2019https://t.co/JUWpuAhcYf
— hardmaru (@hardmaru) November 29, 2019
