78% MNIST accuracy using GZIP in under 10 lines of code
1–10 of 141 posts
Re: 78% MNIST accuracy using GZIP in under 10 lines of code
#2I wonder why you started with a code-golfed version? That seems original to the main point of the post
Re: 78% MNIST accuracy using GZIP in under 10 lines of code
#3I wonder why you started with a code-golfed version? That seems original to the main point of the post
original -> orthogonal?
I like short code! It's like a joke "this is so easy, 10 loc" :)
Re: 78% MNIST accuracy using GZIP in under 10 lines of code
#4[flagged]
Re: 78% MNIST accuracy using GZIP in under 10 lines of code
#5I wonder why you started with a code-golfed version? That seems original to the main point of the post
original -> orthogonal? I like short code! It's like a joke "this is so easy, 10 loc" :)
The internet has turned into a game of “is it him or is it autocorrect?”
I can’t count how many times I’ve looked up at a line of text to spot check it, type in a couple more letters, hit save without looking, and find later that I sound like I’m having a stroke. Never mind the times I’ve simply forgotten to look. Yes that’s a word, stop trying to replace it.
(Five minutes ago I had to type “laissez-faire” three times. Yesterday it turned “understanding” into god knows what. And if iOS doesn’t stop adding apostrophes to “its” I’m gonna fuckin lose my shit)
Re: 78% MNIST accuracy using GZIP in under 10 lines of code
#6[flagged]
MNIST (and OCR) are acronyms that are so well-known to anyone who has taken any kind of intro to ML class that there's no more need to define them in a short blog post than there would be for us to define HTML. I learned about MNIST in 2008, and I was just taking a class on numerical methods as a physics major in Matlab where MNIST was just one project.
Re: 78% MNIST accuracy using GZIP in under 10 lines of code
#7[flagged]
[flagged]
Re: 78% MNIST accuracy using GZIP in under 10 lines of code
#8What explains the huge difference in perf with the approach from 2019 mentioned at the end?
For image classification, couldn't one use the residual from applying a jpeg codebook learned on a training example as metric?
Re: 78% MNIST accuracy using GZIP in under 10 lines of code
#9Re: 78% MNIST accuracy using GZIP in under 10 lines of code
#10[flagged]
> Such as OCR.
Such as what?