Module dfdx::nn

Neural network building blocks such as Linear and impls for tuples as feedforward networks.

Structs

Abs

Struct that impls Module as calling [$func_name] on self.

Cos

Struct that impls Module as calling [$func_name] on self.

Exp

Struct that impls Module as calling [$func_name] on self.

Linear

A linear transformation of the form xW + b, where W is a matrix, x is a vector or matrix, and b is a vector. If x is a matrix this does matrix multiplication.

Ln

Struct that impls Module as calling [$func_name] on self.

ReLU

Struct that impls Module as calling [$func_name] on self.

Sigmoid

Struct that impls Module as calling [$func_name] on self.

Sin

Struct that impls Module as calling [$func_name] on self.

Sqrt

Struct that impls Module as calling [$func_name] on self.

Square

Struct that impls Module as calling [$func_name] on self.

Tanh

Struct that impls Module as calling [$func_name] on self.

Traits

Module

A unit of a neural network. Acts on the generic Input and produces Module::Output.