NN-SVG is a tool for creating Neural Network architecture drawings parametrically rather than manually!
It also provides the ability to export those drawings to Scalable Vector Graphics (SVG) files, suitable for inclusion in academic papers or web pages
https://t.co/eQAqTUT9Sc
When your success is determined by objective reality -- user adoption, economic viability -- you're incentivized to deliver. When your success is determined by convincing people that your ideas are right and important, you're incentivized to deceive...
Because deep learning is so empirical, success in it is to a large extent proportional to raw experimental throughput - the ability to babysit a large number of experiments at once, staring at plots and tweaking/re-launching what works. This is necessary, but not sufficient.
Finding it increasingly hard to keep up with all of the activity in deep learning right now, as # tabs -> \infty and tab width -> 0. It hasn't even been a decade since AlexNet (~Sep 2012 => ~8.5yrs) and a lot happened. Another 8.5 will be ~2030, I wonder what that's like.
@chren_b दरिद्र नाऊँ नरमा छ कस्को ?
विशाल तृष्णा घरमा छ जस्को ।
कुन् हो धनी सब् नरले कह्याको ?
सन्तोषले जो छ खुसी रह्याको ||
(Happy Birthday to the writer!)