package tiny_libs

  1. Overview
  2. Docs
From-scratch libraries for teaching: graphics, audio, compression, crypto, networking and more

Install 

dune-project
 Dependency

github.com Readme Edit opam file Versions (1)

Authors

  1. Y
    Yoann Padioleau <yoann.padioleau@gmail.com

Maintainers

  1. Y
    Yoann Padioleau <yoann.padioleau@gmail.com

Sources

0.3.6.tar.gz
md5=7c636383d146d30ac6f2fa234a6253c8
sha512=c79f3823c5f8f57e5038eb640d487c61168b84aa07c61999d6622ef9fd0c890e2b03b4c6a7cdbbe9352a49e25dda00ac7bb14693cee8e3d7beeed251351a2af0

doc/tiny_libs.ai_learning/Backprop/index.html

Module BackpropSource

Sourcetype example = float array * float array
Sourcetype grads = (Matrix.t * Matrix.t) list
Sourceval loss : Net.t -> example list -> float
Sourceval gradient : Net.t -> example -> grads
Sourceval over : Net.t -> example list -> grads
Sourceval step : rate:float -> Net.t -> grads -> Net.t
Sourceval learn : ?rate:float -> Net.t -> example list -> Net.t
Sourceval numeric : ?epsilon:float -> Net.t -> example list -> grads
Sourceval magnitudes : grads -> float list