Neuron.Activation
type typ =
| Elu
| Relu
| Sigmoid
| HardSigmoid
| Softmax of int
| Softplus
| Softsign
| Tanh
| Relu6
| LeakyRelu of float
| TRelu of float
| Custom of Optimise.Algodiff.t -> Optimise.Algodiff.t
| None
Types of activation functions.
*)type neuron_typ = {
mutable activation : typ;
mutable in_shape : int array;
mutable out_shape : int array;
}
Neuron type definition.
val create : typ -> neuron_typ
Create the neuron.
val connect : int array -> neuron_typ -> unit
Connect this neuron to others in a neural network.
val run_activation : Optimise.Algodiff.t -> typ -> Optimise.Algodiff.t
Run one specific activation function.
val copy : neuron_typ -> neuron_typ
Make a deep copy of the neuron and its parameters.
val run : Optimise.Algodiff.t -> neuron_typ -> Optimise.Algodiff.t
Execute the computation in this neuron.
val activation_to_string : typ -> string
Return the name of a specific activation function.
val to_string : neuron_typ -> string
Convert the neuron to its string representation. The string is often a summary of the parameters defined in the neuron.