module Annet: `sig`

.. `end`

ANNiML main functions.

val anniml_training : `string -> string -> string -> int * Ann_func.vector`

`anniml_training fnet fwts fpatterns`

returns a couple `(i,w)`

where `i`

is the iteration at which the training stopped, and
`w`

is the resulting weights vector. The network's topology and
weights are also saved in `fnet`

and `fwts`

respectively.

val anniml_test : `string -> string -> string -> unit`

`anniml_test fnet fwts fpatterns`

tests the network with topology
file `fnet`

and weights file `fwts`

, on patterns `fpatterns`

.

`type `

input =

`|` |
`Vector of ``float array` |

`|` |
`Pattern of ``int` |

val anniml_run : `string -> string -> input -> Ann_func.vector`

`anniml_run fnet fwts input`

runs the network with topology file `fnet`

and weights file `fwts`

on an input vector `input`

and returns an
output vector `y`

.

val anniml_predict : `string -> string -> string -> string -> unit`

`anniml_predict fnet fwts finputs fpredict`

makes predictions on a file
of input vectors `finputs`

. The results are saved in file `fpredict`

.