|
|
Boost : |
Subject: Re: [boost] Supporting DNNs with Tensors/Multidimensional Arrays
From: Bjorn Reese (breese_at_[hidden])
Date: 2018-08-30 18:17:29
On 08/29/18 15:47, Cem Bassoy via Boost wrote:
> 2. what are the obligatory, necessary basic operations for creating DNN
> building blocks?
You may want to investigate Automatic Differentiation, which is a
building block that extends to many use cases besides DNN.
A good starting point is this talk by Conal Elliott:
https://www.youtube.com/watch?v=ne99laPUxN4
Boost list run by bdawes at acm.org, gregod at cs.rpi.edu, cpdaniel at pacbell.net, john at johnmaddock.co.uk