Matthew Wilson (@matwilso) 's Twitter Profile
Matthew Wilson

@matwilso

trying to make the future happen

@ tesla autopilot

ID: 793285241515323392

linkhttp://matwilso.github.io calendar_today01-11-2016 02:55:15

133 Tweet

1,1K Takipçi

387 Takip Edilen

Andrej Karpathy (@karpathy) 's Twitter Profile Photo

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.

Elon Musk (@elonmusk) 's Twitter Profile Photo

While it is trivial to enter the United States illegally, it is insanely difficult for legal immigrants to move to the United States. This is madness! We should shut down illegal immigration and greatly increase legal immigration.

Lucas Beyer (bl16) (@giffmana) 's Twitter Profile Photo

It can't be repeated enough: learning-rate is the single most bang-for-buck thing you can tune. If you think you know *ze best* learning-rate, it just means you only train standard stuff! This is not a "secret trick" either; it's stated very clearly in THE deep-learning book:

It can't be repeated enough: learning-rate is the single most bang-for-buck thing you can tune.

If you think you know *ze best* learning-rate, it just means you only train standard stuff!

This is not a "secret trick" either; it's stated very clearly in THE deep-learning book:
Matthew Wilson (@matwilso) 's Twitter Profile Photo

"Certainly coming up with new ideas is important, but I think even more important is to understand the results, to understand the existing ideas, to understand what's going on. ... Figuring out what next experiment to run, a lot of time is spent on that. Understanding what could

David Perell (@david_perell) 's Twitter Profile Photo

Dave Letterman’s advice to Jerry Seinfeld: “Make sure you fail doing exactly what you want to do. That, you can live with.“

Patrick Collison (@patrickc) 's Twitter Profile Photo

T. Greer I think it's stratified by generation, but here's an attempt. (This isn't the list of books that I think one ought to read -- it's just the list that I think roughly covers the major ideas that are influential here.) The Tinkerings of Robert Noyce Seeing Like a State The Dream

Matthew Wilson (@matwilso) 's Twitter Profile Photo

I, Robot is actually more or less the reason I got into robotics/AI in the first place. Near the end of high school, circa 2015, I was watching a bunch of Elon Musk videos and trying to figure out what I wanted to do and what was worth spending time on. I saw the movie as a kid

I, Robot is actually more or less the reason I got into robotics/AI in the first place. Near the end of high school, circa 2015, I was watching a bunch of Elon Musk videos and trying to figure out what I wanted to do and what was worth spending time on. I saw the movie as a kid
Ashok Elluswamy (@aelluswamy) 's Twitter Profile Photo

With the latest release (v12.5.6.3), FSD is using end-to-end neural networks for driving across highways, city streets and parking lots, and has now shipped widely for AI4 vehicles. Highway driving should be smoother, more natural and even safer than the previous explicit

Andrej Karpathy (@karpathy) 's Twitter Profile Photo

Of ~200 books I've read, the few that stayed with me over time and I find myself often thinking back to or referring to, in ~random order: All short stories by Ted Chiang, especially Exhalation, Division By Zero, Understand, The Story of Your Life, Liking What You See, The

Matthew Wilson (@matwilso) 's Twitter Profile Photo

I can give my first impressions. I can think for a few seconds, I can think for 10s of seconds. I can get back to you later. I can get back to you tomorrow. I can spend time writing and revising a whole essay about it, and getting the thoughts well thought out over hours. I can