dritchie

dritchie/adnn

Javascript neural networks on top of general scalar/tensor reverse-mode automatic differentiation.

JavaScript
234
25
MIT License
Total donated
Undistributed
Share with your subscribers:

Recipients

How the donated funds are distributed

Support the repos that depend on dritchie/adnn

Account's avatar
Probabilistic programming for the web
Account's avatar
Semantic parsing for webppl
Account's avatar
adnn provides TypeSafe Javascript-native neural networks on top of general scalar/tensor reverse-mode automatic differentiation. You can use just the AD code, or the NN layer built on top of it. This architecture makes it easy to define big, complex numerical computations and compute derivatives w.r.t. their inputs/parameters. adnn also includes utilities for optimizing/training the parameters of such computations.

Top contributors

dritchie's profile
dritchie
180 contributions
null-a's profile
null-a
11 contributions
carlhopf's profile
carlhopf
2 contributions
Radagaisus's profile
Radagaisus
1 contributions
thomasat's profile
thomasat
1 contributions
dorarad's profile
dorarad
1 contributions
longouyang's profile
longouyang
1 contributions
jpchen's profile
jpchen
1 contributions

Recent events

Kivach works on the Obyte network, and therefore you can track all donations.

No events yet