You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
The ability to understand mathematical processes is widespread, but the ability to parse mathematical notation isn't. Insisting on teaching deep learning (which is fundamentally software engineering, not mathematics) with equations is like insisting on teaching Hegel in German.
See how far you'd get as a software developer if all your object and method names were Greek letters.
> Unlike Julia or Swift, which allow any unicode symbol to represent a variable (including emoji) Python 3 restricts variable names to unicode characters that represent characters in written languages. https://python-3-for-scientists.readthedocs.io/en/latest/python3_features.html#unicode-variable-names …
Not to mention that the code representation has some major intrinsic advantages anyway, like inspectability and enforced precision.
I believe there a middle way between pure engineering and pure mathematics to teach deep learning
Most difficult problem of democratization of AI in particular, technology in general.
I completely agree. This forces the lecturer to widen their understanding of the subject matter, say, by thinking of good analogies that will be intuitive to their audience. Beneficial for both parties.
Found this today
Kha/electrolysis
> Simple verification of Rust programs via functional purification in Lean 2(!)
> A tool for formally verifying Rust programs by transpiling them into definitions in the Lean theorem prover.
#LeanTheorem #TLAhttps://github.com/Kha/electrolysis …
I think the problem is that deep learning is a relatively new field, such as computer science in general. And thus notation is still not consistent nor necessarily easy to parse
This is why I regularly insult PragerU
I feel like Julian Assange in a glass box in the back of a courtroom speaking up to defend myself only to have the judge tell me to talk with my lawyers, who are setting at the front. Leaving me with saying "that's the problem, I can't" Here is why I hear tech industry judge....
be it math or coding, it's all abstraction to manipulate the state of transistors where the actions to do so are unavoidable, gears and bearing of abstraction processing. Done through computers or the human mind these action constants are what enables abstraction processing.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
