~2 hours debugging an issue I thought was due to something I misunderstood in the deep mathematics involved but I just forgot to call `https://t.co/E1f9894p7z_grad()`. This bug really builds character
— Andrej Karpathy (@karpathy) December 8, 2019
~2 hours debugging an issue I thought was due to something I misunderstood in the deep mathematics involved but I just forgot to call `https://t.co/E1f9894p7z_grad()`. This bug really builds character
— Andrej Karpathy (@karpathy) December 8, 2019
There's plenty that I agree with in this article but the thing that I cannot abide is the concept that finding discrimination in privately held, IP-protected algorithms is easy is just plain wrong.https://t.co/ITMwIFJBzW
— Cathy O'Neil (@mathbabedotorg) December 8, 2019
I think 70% of our anxieties about modern technology can be traced back to Western governments transfering big chunks of R&D and expertise from public sector to private sector, which develops things in different ways with different priorities
— Jack Clark (@jackclarkSF) December 8, 2019
DGL (Deep Graph Library) –clean abstraction for building graph-based neural nets atop PyTorch/MxNet. Comes pre-built with auto-batching, sparse-multiplication and 10 different models like GCNs or TreeLSTM
— ML Review (@ml_review) December 7, 2019
Github https://t.co/UgZtFajJJM
Twitter @GraphDeep
Happy Birthday 🎂🎈🎉 pic.twitter.com/K2IoHawsez
Google, Intel, MIT, and more: a NeurIPS conference AI research tour #NeurIPS2019 https://t.co/9zUaFgSeib
— Nando de Freitas (@NandoDF) December 7, 2019
Our team will be presenting Novograd at Beyond First Order Methods in ML and NeMo at MLSys workshops.
— Chip Huyen @ NeurIPS (@chipro) December 7, 2019
I'll be on a panel with some academic heroes of mine to discuss research vs industry at NewInML, 3pm Monday.
Hit me up if you want to chat! #NeurIPS2019https://t.co/WHzcfh7pG0
Geographical distributions of the USA’s burger chains. #datavizhttps://t.co/UVEqEVDeyC pic.twitter.com/EEqdUxYVtB
— Randy Olson (@randal_olson) December 7, 2019
Very commendable. We need more of this. These companies letting China’s oppressive government steer the direction of the rest of the world for short term gain, comfort and greed is the epitome of cowardice. https://t.co/Oke5BUBvhV
— Jason Antic (@citnaj) December 7, 2019
Based on emergency room data, here are all the foreign bodies that got stuck down there.
— Nathan Yau (@flowingdata) December 6, 2019
If you choose to venture, make sure you have a good grip. There's a vacuum suction effect I am told. https://t.co/C7qz98iVfB
TF 2.1 is coming soon (RC0 out now), with extended TPU support: https://t.co/aqv7xTB2Bu (via @martin_gorner)
— François Chollet (@fchollet) December 6, 2019
love too walrus comprehension #python pic.twitter.com/BjAWb6PkpU
— Joel Grus 👼👼👼 (@joelgrus) December 6, 2019
How does transfer learning for medical imaging affect performance, representations and convergence? In a new #NeurIPS2019 paper, we investigate this across different architectures and datasets, finding some surprising conclusions! Learn more below: https://t.co/svZY5sUJEu
— Google AI (@GoogleAI) December 6, 2019