Re:Vis: A Vim-Like Text Editor
by gcr on Thursday April 07, 2016 @09:04AM
(#11446884)
Just jumping off your last sentence: "Simplicity" and "Transparency" are orthogonal.
In the case of deep learning, all current state-of-the-art models can be expressed as nothing more than matrix multiplication, addition, and clipping. That's all you need. It's so simple: multiply, add, clip. Multiply, add, clip.
But the model isn't transparent. It's clear what each step is doing (multiply! add! clip!), but it's not clear to the human why that's necessary.
In the case of deep learning, all current state-of-the-art models can be expressed as nothing more than matrix multiplication, addition, and clipping. That's all you need. It's so simple: multiply, add, clip. Multiply, add, clip.
But the model isn't transparent. It's clear what each step is doing (multiply! add! clip!), but it's not clear to the human why that's necessary.