v4r

I remember there was a very nice website to draw things with touchpad that was mentioned on HN but I couldn't find it in my history. It could be used for signature too I suppose.

I'm working on a project using kd-tree for high-dimensional embeddings. Could you send me some pointers?

This is first-world first-class university privilege right here.

What is your opinion on network representation learning? Can it be used in Dgraph? For instance, do you think it is possible to use node embeddings as indices for faster retrieval?

If a model involves a lot of math, is it more helpful to be able to debug it? What tf lacks is an intuitive debugging tool. I think this is where pytorch excels.