skierscott
Joined 14 years ago
Karma
406
Submissions
180
Member since
Feb 8
Recent submissions
Comment · 8 years ago
Comment · 8 years ago
mpi4py is a solid implementation, but the docs aren’t the greatest, especially if you’re not familiar with MPI.
Comment · 8 years ago
On iOS this isn’t functional. I can’t advance past the first slide.
Comment · 8 years ago
>> Going forward, GitHub will remain an open platform, which any developer can plug into and extend.
Does an “open platform” mean “open source” or “a plugin system”? I think making it open source would alleviate a lot of dev concerns.
Comment · 8 years ago
> Some states destroy the blood spots after a year, 12 states store them for at least 21 years.
What are the other 12 states?
Comment · 8 years ago
My favorite is Alan Turings quote:
> Mathpix's AI definitely passes THIS Turing test!
Comment · 8 years ago
Isn’t this what JITs do?
Comment · 8 years ago
> “If you understand and agree, Apple and GCBD have the right to access your data stored on its servers. This includes permission sharing, exchange, and disclosure of all user data (including content) according to the application of the law.”
> In other words, once the agreement is signed, GCBD — a company solely owned by the state — would get a key that can access all iCloud user data in China, legally.
What user data will this decrypt? Are iMessage and FaceTime still safe?
Comment · 8 years ago
There’s also a closed form for the Fibonacci numbers. It runs in O(1).
http://stsievert.com/blog/2015/01/31/the-mysterious-eigenval...
Comment · 9 years ago
Not true. Infinite sums are not defined for series that don’t converge, and sum(1..n) does not converge as n => infinity.
Yes, you can play a nice trick with that sum if you ignore the fact that inf-inf is meaningless.
Comment · 9 years ago
Where does Apple Notes store it’s files? What format are they in?
Comment · 9 years ago
Wow, great demo. Even works on mobile!
Comment · 9 years ago
> 2% is HUGE at this point
Hell, on MNIST 0.14% is huge. Geff Hinton created an entire new architecture to get 0.25% error, which is far better than the baseline 0.39% error [1].
To be fair, he did reduce the error by 35%.
Comment · 9 years ago
> what has changed in Python 3.6 that they're happy to do this now when they were pissed off about it a couple years ago?
Most of mine have to do with developer productovity and I didn’t find until Python 3.5.
– @, the matmul operator
– fstrings (f”{foo}”)
– parameter typing (foo: int = 0) which has exciting work with Cython
– other async features. I forget what library it was (tensorflow?) but for Python 3 it had better async support
Neural nets should return a low confidence score. But, the popular approach (described below) ignores that. Neural nets ignore confidence because of a technique called softmax [1].
This happens as the final operation of a neural net, and is required for training.
Softmax is a tool to make an array of positive numbers look like a probability distribution:
x[i] is a class prediction, but x.sum() != 1. Say if the network was uncertain, x[cat, dog] = [0.03, 0.01]. These are small values that do not imply great confidence (the network was trained on vectors with out.sum() = 1. The network would predict “dog” using softmax because out[dog] = 0.75 > 0.25 = out[cat].But then in inference/prediction, the confidence is ignored. What if x.sum() is small? That would imply that the network is uncertain.
[1]: https://en.m.wikipedia.org/wiki/Softmax_function