nz::nodes::calc::TanhNode Class Reference

Represents a hyperbolic tangent (tanh) activation function node in a computational graph. More...

Inheritance diagram for nz::nodes::calc::TanhNode:

Collaboration diagram for nz::nodes::calc::TanhNode:

Public Member Functions
	TanhNode (Node *input)
	Constructor to initialize a TanhNode for applying the tanh activation function.
void	forward () override
	Forward pass for the TanhNode to apply the tanh activation function.
void	backward () override
	Backward pass for the TanhNode to compute gradients.
Public Member Functions inherited from nz::nodes::Node
virtual void	print (std::ostream &os) const
	Prints the type, data, and gradient of the node.
void	dataInject (Tensor::value_type *data, bool grad=false) const
	Injects data into a relevant tensor object, optionally setting its gradient requirement.
template<typename Iterator >
void	dataInject (Iterator begin, Iterator end, const bool grad=false) const
	Injects data from an iterator range into the output tensor of the InputNode, optionally setting its gradient requirement.
void	dataInject (const std::initializer_list< Tensor::value_type > &data, bool grad=false) const
	Injects data from a std::initializer_list into the output tensor of the Node, optionally setting its gradient requirement.

Detailed Description

Represents a hyperbolic tangent (tanh) activation function node in a computational graph.

The TanhNode class applies the hyperbolic tangent (tanh) activation function to the input tensor. The tanh function is defined as:

Tanh(x) = (exp(x) - exp(-x)) / (exp(x) + exp(-x))

It maps input values to the range (-1, 1) and is commonly used in neural networks for non-linear activation.

Key features:

• Forward Pass: Applies the tanh activation function element-wise to the input tensor, mapping values to the range (-1, 1).
• Backward Pass: Computes the gradient of the loss with respect to the input tensor using the derivative of the tanh function, which is:

  Tanh'(x) = 1 - Tanh(x)^2

• Shape Preservation: The output tensor has the same shape as the input tensor.
• Gradient Management: Automatically tracks gradients if required by the input tensor.

This class is part of the nz::nodes namespace and is commonly used to add non-linearity to models or normalize outputs.

Note

• The tanh function is applied element-wise, mapping the input tensor to the range (-1, 1).
• Efficient GPU computations are performed for both forward and backward passes.

Usage Example:

// Example: Using TanhNode in a computational graph
InputNode input({3, 3}, true);  // Create an input node with shape {3, 3}
 
float data[] = {-1.0f, 0.0f, 1.0f, 2.0f, -2.0f, 3.0f, -3.0f, 4.0f, -4.0f};  // Sample input values
input.output->dataInject(data);  // Copy data to the input tensor
 
TanhNode tanh_node(&input);  // Apply tanh activation
tanh_node.forward();  // Perform the forward pass
tanh_node.backward();  // Propagate gradients in the backward pass
 
std::cout << "Output: " << *tanh_node.output << std::endl;  // Print the result

See also

forward() for the tanh activation computation in the forward pass.

backward() for gradient computation in the backward pass.

Author

Mgepahmge (https://github.com/Mgepahmge)

Date

2024/12/05

Definition at line 2214 of file Nodes.cuh.

Constructor & Destructor Documentation

TanhNode()

nz::nodes::calc::TanhNode::TanhNode ( Node * input )

explicit

Constructor to initialize a TanhNode for applying the tanh activation function.

The constructor initializes a TanhNode, which applies the hyperbolic tangent (tanh) activation function to an input tensor. It establishes a connection to the input node, initializes the output tensor, and sets the type of the node to "Tanh".

Parameters

input

A pointer to the input node. Its output tensor will have the tanh activation applied.

• The input node is added to the inputs vector to establish the connection in the computational graph.
• The output tensor is initialized with the same shape as the input tensor, and its gradient tracking is determined based on the input tensor's requirements.
• The node's type is set to "Tanh" to reflect its operation.

Note

• The tanh activation function maps input values to the range (-1, 1) and is defined as:

  Tanh(x) = (exp(x) - exp(-x)) / (exp(x) + exp(-x))

• This node supports automatic gradient tracking if the input tensor requires gradients.

See also

forward() for the forward pass implementation.

backward() for gradient computation in the backward pass.

Author

Mgepahmge (https://github.com/Mgepahmge)

Date

2024/12/05

Definition at line 387 of file Nodes.cu.

Member Function Documentation

backward()

void nz::nodes::calc::TanhNode::backward ( )

overridevirtual

Backward pass for the TanhNode to compute gradients.

The backward() method computes the gradient of the loss with respect to the input tensor by applying the derivative of the tanh activation function. The gradient is propagated using the formula:

Tanh'(x) = 1 - Tanh(x)^2

• A CUDA kernel (TanhBackward) is launched to compute the gradients in parallel on the GPU.
• The derivative of the tanh function is applied element-wise to the output tensor's data and combined with the gradient of the output tensor to compute the input gradient.
• The computed gradient is stored in the gradient tensor of the input node.

Note

• Gradients are only computed and propagated if the input tensor's requiresGrad property is true.
• The shape of the gradient tensor matches that of the input tensor.

See also

forward() for the tanh activation computation in the forward pass.

Author

Mgepahmge (https://github.com/Mgepahmge)

Date

2024/12/05

Implements nz::nodes::Node.

Definition at line 400 of file Nodes.cu.

Here is the call graph for this function:

forward()

void nz::nodes::calc::TanhNode::forward ( )

overridevirtual

Forward pass for the TanhNode to apply the tanh activation function.

The forward() method applies the hyperbolic tangent (tanh) activation function element-wise to the input tensor. The result is stored in the output tensor. The tanh function is defined as:

Tanh(x) = (exp(x) - exp(-x)) / (exp(x) + exp(-x))

It maps input values to the range (-1, 1).

• A CUDA kernel (Tanh) is launched to compute the activation function in parallel on the GPU.
• The grid and block dimensions are dynamically calculated based on the size of the output tensor to optimize GPU utilization.
• The computed values are stored in the output tensor for use in subsequent layers or operations.

See also

backward() for the computation of gradients in the backward pass.

Author

Mgepahmge (https://github.com/Mgepahmge)

Date

2024/12/05

Implements nz::nodes::Node.

Definition at line 394 of file Nodes.cu.

Here is the call graph for this function:

---

The documentation for this class was generated from the following files:

• D:/Users/Mgepahmge/Documents/C Program/NeuZephyr/include/NeuZephyr/Nodes.cuh
• D:/Users/Mgepahmge/Documents/C Program/NeuZephyr/src/Nodes.cu