ryanrhymes

let backprop nn eta x y =
  let t = tag () in
  Array.iter (fun l ->
    l.w <- make_reverse l.w t;
    l.b <- make_reverse l.b t;
  ) nn.layers;
  let loss = Maths.(cross_entropy y (run_network x nn) / (F (Mat.row_num x |> float_of_int))) in
  reverse_prop (F 1.) loss;
  Array.iter (fun l ->
    l.w <- Maths.((primal l.w) - (eta * (adjval l.w))) |> primal;

ryanrhymes

let test_model nn x y =
  Mat.iter2_rows (fun u v ->
    Dataset.print_mnist_image (unpack_mat u);
    let p = run_network u nn |> unpack_mat in
    Owl.Mat.print p;
    Printf.printf "prediction: %i\n" (let _, _, j = Owl.Mat.max_i p in j)
  ) x y

let _ =
  let x, _, y = Dataset.load_mnist_train_data () in

ryanrhymes

(* Owl Lib: https://github.com/ryanrhymes/owl *)

open Owl_ext;;

let a = F 5.;;                             (* float number     *)
let b = C Complex.({re = 2.; im = 5.});;   (* complex number   *)
let x = Dense.Matrix.S.uniform 3 3;;       (* float32 matrix   *)
let y = Dense.Matrix.D.uniform 3 3;;       (* float64 matrix   *)
let z = Dense.Matrix.Z.uniform 3 3;;       (* complex64 matrix *)

ryanrhymes

#require "owl_neural";;
open Owl_neural;;

let nn = Feedforward.create ();;
let l0 = linear ~inputs:784 ~outputs:300 ~init_typ:(Init.Uniform (-0.075,0.075));;
let l1 = linear ~inputs:300 ~outputs:10 ~init_typ:(Init.Uniform (-0.075,0.075));;
Feedforward.add_layer nn l0;;
Feedforward.add_activation nn Activation.Tanh;;
Feedforward.add_layer nn l1;;
Feedforward.add_activation nn Activation.Softmax;;

ryanrhymes

#require "owl_neural";;
open Owl_neural;;

(* config the neural network *)
let nn = Feedforward.create ();;
let l0 = linear ~inputs:784 ~outputs:300 ~init_typ:Init.(Uniform (-0.075,0.075));;
let l1 = linear ~inputs:300 ~outputs:10 ~init_typ:Init.(Uniform (-0.075,0.075));;
Feedforward.add_layer nn l0;;
Feedforward.add_activation nn Activation.Tanh;;
Feedforward.add_layer nn l1;;

ryanrhymes

#require "owl_neural";;
open Owl_neural;;

(* config the neural network *)
let nn = Feedforward.create ();;
let l0 = linear 784 300 ~init_typ:Init.(Uniform (-0.075,0.075));;
let l1 = linear 300 10 ~init_typ:Init.(Uniform (-0.075,0.075));;
Feedforward.add_layer nn l0 ~act_typ:Activation.Tanh;;
Feedforward.add_layer nn l1 ~act_typ:Activation.Softmax;;
print nn;;

ryanrhymes

```ocaml
Mat.map (min 5.) x;;
```


```ocaml
let x = Mat.uniform 5 5;;
Mat.filter (( < ) 0.5) x;;
...
```

ryanrhymes

function f00()
  x = rand(1000, 2000)
  t0 = time()
  LinAlg.LAPACK.gesvd!('A','A',x)
  t1 = time()
  @printf "time:\t\t%.8f\n" (t1 -t0)
end


function f00()

ryanrhymes

module CI = Cstubs_internals

external owl_stub_1_LAPACKE_sbdsdc
  : int -> char -> char -> int -> _ CI.fatptr -> _ CI.fatptr ->
    _ CI.fatptr -> int -> _ CI.fatptr -> int -> _ CI.fatptr -> _ CI.fatptr ->
    int = "owl_stub_1_LAPACKE_sbdsdc_byte12" "owl_stub_1_LAPACKE_sbdsdc" 

external owl_stub_2_LAPACKE_dbdsdc
  : int -> char -> char -> int -> _ CI.fatptr -> _ CI.fatptr ->
    _ CI.fatptr -> int -> _ CI.fatptr -> int -> _ CI.fatptr -> _ CI.fatptr ->

ryanrhymes

let x = Mat.uniform 4 4;;
let x = Mat.symmetric x;;
let v, w = Linalg.D.eig x;;
let w = Dense.Matrix.Z.re w;;
let v = Dense.Matrix.Z.re v;;
let v0 = Mat.col v 0;;
let a = Mat.(x *@ v0);;
let b = Mat.(v0 *$ w.{0,0});;
Mat.(a =~ b);;