L1: Tensor Studio — An in-browser live-programming environment for differentiable tensor computations (written on top of TensorFlow.js) by Milan Lajtoš
— Nikhil Thorat (@nsthorat) July 29, 2018
Live demo: https://t.co/2GfLMRht2j
Github: https://t.co/95Wz4BvvVU pic.twitter.com/srYtJcLvj0
Here's that shared parameterization in action. Note how the visualizations are easier to compare when visual landmarks stay in place.https://t.co/FokUCWvQze pic.twitter.com/5zpF8f3wJ5
— Ludwig Schubert (@ludwigschubert) July 25, 2018
Differentiable Image Parameterizations - A new Distill article by @zzznah @nicolapezzotti @ludwigschubert & @ch402 https://t.co/48BaSim6bQ
— distillpub (@distillpub) July 25, 2018
A powerful, under-explored tool for neural network visualizations and art.
Samples from CPPN-GAN trained on Chinese handwriting dataset https://t.co/U1wc8qXLME pic.twitter.com/1rXwUttH5z
— hardmaru (@hardmaru) July 24, 2018
Something for fun: https://t.co/Y9MLqQotm8. Use #Rstats to generate ur own modern art in the style of Mondrian, apply stylistic low-res pixelated filter to ur photos, and more. All code available. Print at home. Inspired by @accidental__aRt and @R_Graph_Gallery #creativecoding pic.twitter.com/1uAb1Di0gg
— Jean Fan (@JEFworks) July 22, 2018
🗺 fancy map viz, w/ code!
— Mara Averick (@dataandme) July 21, 2018
"Regional population structures at a glance" 🖊 @ikashnitskyhttps://t.co/wRecy2xwVB#rstats #ggplot2 pic.twitter.com/7C9AVMgU7D
Code for the Glow demo is now on github! Use the pre-trained model to create manipulation vectors from your own labelled dataset (eg: changing hair color to red). You can also run the demo locally, go make your own smiling videos!https://t.co/kLTURsLX0d pic.twitter.com/05T3gzs9gg
— Prafulla Dhariwal (@prafdhar) July 21, 2018
This is a neat intro to both Gumbel Softmax and GANs in a single post. I like how the full post is written in a Jupyter notebook. https://t.co/GMdJrIGPsi
— Denny Britz (@dennybritz) July 20, 2018
Universal Transformers propose to augment Transformers with Recurrence in depth and Adaptive Computation Time. This model outperforms Vanilla Transformers in MT / bAbI / LA / LTE.
— Oriol Vinyals (@OriolVinyalsML) July 12, 2018
Paper: https://t.co/U2YAeuO6EO
Code: Soon in https://t.co/KSuQAkn5Jh pic.twitter.com/lCKfsEAswG
Code for this paper https://t.co/XolvOYZzXQ
— Tim Vieira (@xtimv) July 8, 2018
- Code is very readable (Python) and includes some neat tricks
- Uses scikit-learn as the base algorithm https://t.co/fXOjPJSJDj
code and pre-trained models to reproduce the recent paper "Scaling Neural Machine Translation" (https://t.co/mrRDmlwax1) where we train on up to 128 GPUs with half precision floating point operations as well as delayed batching.
— PyTorch (@PyTorch) June 16, 2018
Explore the SmoothGrad feature saliency technique in an Observable notebook with TensorFlow.js by @aman_gif.
— TensorFlow (@TensorFlow) June 14, 2018
Learn more here → https://t.co/rKbJ57yRH0 pic.twitter.com/bnJnzgR5S9
