Tanh: Trigonometric Tanh

In frhl/neuralnetr: Neural Nets in R

Description

Each activation module has a forward method that takes in a batch of pre-activations Z and returns a batch of activations A.

Super class

neuralnetr::ClassModule -> Tanh

Public fields

A

the activation vector

Methods

Public methods

• Tanh$forward()

• Tanh$backward()

• Tanh$clone()

Inherited methods

• neuralnetr::ClassModule$sgd_step()

---

Method forward()

Usage

Tanh$forward(Z)

Arguments

Z

a vector of pre-activations

Returns

a vector of activations.

---

Method backward()

Usage

Tanh$backward(dLdA)

Arguments

dLdA

vector of gradients.

Returns

a vector gradients.

---

Method clone()

The objects of this class are cloneable with this method.

Usage

Tanh$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

See Also

Other activation: ReLU, Sigmoid, SoftMax

frhl/neuralnetr documentation built on Nov. 9, 2020, 2:24 p.m.