Viewing profile — rkaplan

This is the correct answer. A key reason Rebco is so much better than older alternatives is that it can be cooled to superconductivity using only liquid nitrogen (77K), as opposed …

Longtime DVC user here - this is going to be so helpful. We use DVC for all of our model and data versioning, but what's been missing is the ability to cleanly integrate that into …

Great anecdote from Jeff Dean's twitter [1] about how they thought to try this experiment, given that doctors didn't know such a thing was possible: "Funny story. We had a new team…

This is not "AI that builds AI". The actual research behind AutoML is called NASNet ( https://arxiv.org/pdf/1707.07012.pdf ), and all it is simply: we found two good neural network…

The AI Grant fellowship has been an awesome experience so far; I highly recommend applying if you're on the fence. The grant itself is useful (and this round includes $20k of Googl…

This post doesn't even mention the easiest way to use deep learning without a lot of data: download a pretrained model and fine-tune the last few layers on your small dataset. In m…

"In contrast to deep neural networks which require great effort in hyper-parameter tuning, gcForest is much easier to train." Hyperparameter tuning is not as much of an issue with …

This paper is important for a few reasons: - Labeled data is very expensive. Historically attempts to learn on synthetic data has failed because ConvNets are very good at detecting…

This paper builds off of DeepMind's previous work on differentiable computation: Neural Turing Machines. That paper generated a lot of enthusiasm when it came out in 2014, but not …