Re:Neural Networks, Types, and Functional Programming
by noelwelsh on Thursday September 03, 2015 @04:09PM
(#10167226)
If this formalism works out then a few interesting directions spring to mind:
- we suddenly have a huge new toolbox from FP / category theory that we can apply to understanding and extending DNNs. E.g. what happens if we apply differentiation in the manner of zippers to these structures? I have no idea but it might lead somewhere.
- The deep learning world gets a precise way to describe network architecture which makes communication much easier and research much more reproducible.
- With a formal model you can automate building and optimising implementations.
- we suddenly have a huge new toolbox from FP / category theory that we can apply to understanding and extending DNNs. E.g. what happens if we apply differentiation in the manner of zippers to these structures? I have no idea but it might lead somewhere.
- The deep learning world gets a precise way to describe network architecture which makes communication much easier and research much more reproducible.
- With a formal model you can automate building and optimising implementations.