This is a cool Colaboratory notebook that shows how you can apply ML and NLP to the content of your own @feedly feeds.https://t.co/9RTmkiF539 pic.twitter.com/HqebWvl0AE
— Sebastian Ruder (@seb_ruder) January 28, 2019
This is a cool Colaboratory notebook that shows how you can apply ML and NLP to the content of your own @feedly feeds.https://t.co/9RTmkiF539 pic.twitter.com/HqebWvl0AE
— Sebastian Ruder (@seb_ruder) January 28, 2019
.@AllanDButler used #tidyverse tools like broom, tidyquant and timetk to analyze and predict Super Bowl sales. A really useful case study in forecasting! 🏈💸 https://t.co/NgC1m6sie7 #datablog pic.twitter.com/dqaiPGNpjA
— David Robinson (@drob) January 25, 2019
Amazing new application: paste the text of a programming problem in to the app, and it automatically suggests techniques to solve the problem.
— Jeremy Howard (@jeremyphoward) January 24, 2019
Uses ULMFiT and fastai/@PyTorch.https://t.co/Td8mqKKwzN
This is extremely cool Mudano, a project management company, shows how to use fastai's pretrained NLP @pytorch language model and transfer learning to rapidly build a classifier for project status reports.
— Jeremy Howard (@jeremyphoward) January 18, 2019
Really nice end-to-end walkthru of full model training process. https://t.co/lMbURQk7tc
A chatbot that learns by chatting.
— Yann LeCun (@ylecun) January 17, 2019
Brought to you by FAIR.
"Learning from Dialogue after Deployment: Feed Yourself, Chatbot!", by Braden Hancock, Antoine... https://t.co/rbnsUWDdJf
Manifold looks like an amazing tool I'd love to use. From the post it seems like it's not publicly available and there are no plans to open source it. What's the purpose of promoting internal tools? I wonder how many people wasted time looking for the code after reading this... https://t.co/M3Kb8Nm8SO
— Denny Britz (@dennybritz) January 16, 2019
Desnapify: cool project about training a pix2pix-like model to remove Snapchat filters from pictures https://t.co/H2hWAQmBKM pic.twitter.com/rV9D4D4eL7
— François Chollet (@fchollet) January 14, 2019
Object detection using @fastai with only 300 examples in the training set.
— Radek Osmulski (@radekosmulski) December 31, 2018
Total train time: 3 min
Please note the model definition - again very few lines of code. Annotated images myself - details in the NB. Shown in red are predictions.https://t.co/A1oYorlVOB pic.twitter.com/L8JvPzKJw8
Siamese network using @fastdotai for the @kaggle Whale Identification Challenge is here! https://t.co/0QNGcw7kr3
— Radek Osmulski (@radekosmulski) December 28, 2018
This is the unabridged, slightly messy version, but I feel okay about this. We are stepping outside what @fastdotai does out of the box and at this point I don't feel
#MachineLearning Classification Methods and #AlgorithmicTrading Investing Applications (spoiler: the results are pretty good): https://t.co/lHbKWmoBCf #DataScience #Algorithms #BigData #XGBoost pic.twitter.com/P7EyGN1M0y
— Kirk Borne (@KirkDBorne) December 24, 2018
The speech team @ FAIR released wav2letter++:
— Soumith Chintala (@soumithchintala) December 21, 2018
- a fully convolutional speech recognition system
- a C++ ML library on top of ArrayFire
They recognized very early that C++ was their best option and dived in much before PyTorch C++ API existed.
See: https://t.co/mXmZ3d8Tab
Last minute holiday shoppers will appreciate this one — ML-Powered Product categorization for smart shopping options | by Abhimanyu Sundar via @TDataScience https://t.co/wFmLiLDqK2 pic.twitter.com/Uusypa9elW
— Kaggle (@kaggle) December 18, 2018