_alwc's profile picture.

Alex Lee

@_alwc

TIL the examples on cppreference.com are runnable (and editable too) on the website!

The massive collection of editable, online-runnable, wonderfully constructed examples of C++ use at cppreference might just be the best way to learn modern C++. Such a magnificent and under-appreciated resource. en.cppreference.com/w/cpp/numeric/…

jeremyphoward's tweet image. The massive collection of editable, online-runnable, wonderfully constructed examples of C++ use at cppreference might just be the best way to learn modern C++.

Such a magnificent and under-appreciated resource.
en.cppreference.com/w/cpp/numeric/…


A lab journal on how the authors systematically find a way to optimize NN model size, model accuracy and inference time. Result from the journal: arxiv.org/abs/1806.03723

Just came across the markdown journal for the fast-deepnets project. Really nice to read through a journal taking through the project's evolution. I usually maintain such a journal per project, but privately and not as pretty. github.com/mitdbg/fastdee…



Alex Lee đã đăng lại

Think BatchNorm helps training due to reducing internal covariate shift? Think again. (What BatchNorm *does* seem to do though, both empirically and in theory, is to smoothen out the optimization landscape.) (with @ShibaniSan @tsiprasd @andrew_ilyas) arxiv.org/abs/1805.11604

aleks_madry's tweet image. Think BatchNorm helps training due to reducing internal covariate shift? Think again. (What BatchNorm *does* seem to do though, both empirically and in theory, is to smoothen out the optimization landscape.) (with @ShibaniSan @tsiprasd @andrew_ilyas) arxiv.org/abs/1805.11604

Loading...

Something went wrong.


Something went wrong.