Interface ILossFunction<T>

Namespace

AiDotNet.Interfaces

Assembly

AiDotNet.dll

Interface for loss functions used in neural networks.

public interface ILossFunction<T>

Type Parameters

T

The numeric type used for calculations (e.g., float, double).

Extension Methods

LossFunctionExtensions.ComputeGradient<T>(ILossFunction<T>, Tensor<T>, Tensor<T>)

LossFunctionExtensions.ComputeLoss<T>(ILossFunction<T>, Tensor<T>, Tensor<T>)

Remarks

For Beginners: Loss functions measure how far the predictions of a neural network are from the expected outputs. They provide a signal that helps the network learn by adjusting its weights to minimize this "loss" value.

Think of a loss function as a score that tells you how well or poorly your neural network is performing. A higher loss value means worse performance, while a lower loss value indicates better performance.

Different types of problems require different loss functions. For example:

• Mean Squared Error is often used for regression problems (predicting numeric values)
• Cross Entropy is commonly used for classification problems (categorizing inputs)

The derivative of a loss function is equally important, as it tells the network which direction to adjust its weights during training to reduce the loss.

Methods

CalculateDerivative(Vector<T>, Vector<T>)

Calculates the derivative (gradient) of the loss function.

Vector<T> CalculateDerivative(Vector<T> predicted, Vector<T> actual)

Parameters

predicted Vector<T>

The predicted values from the model.

actual Vector<T>

The actual (target) values.

Returns

Vector<T>

A vector containing the derivatives of the loss with respect to each prediction.

CalculateLoss(Vector<T>, Vector<T>)

Calculates the loss between predicted and actual values.

T CalculateLoss(Vector<T> predicted, Vector<T> actual)

Parameters

predicted Vector<T>

The predicted values from the model.

actual Vector<T>

The actual (target) values.

Returns

T

The loss value.

CalculateLossAndGradientGpu(IGpuTensor<T>, IGpuTensor<T>)

Calculates both loss and gradient on GPU in a single pass.

(T Loss, IGpuTensor<T> Gradient) CalculateLossAndGradientGpu(IGpuTensor<T> predicted, IGpuTensor<T> actual)

Parameters

predicted IGpuTensor<T>

The predicted GPU tensor from the model.

actual IGpuTensor<T>

The actual (target) GPU tensor.

Returns

(T Loss, IGpuTensor<T> Gradient)

A tuple containing the loss value and gradient tensor.

Remarks

This method is more efficient than calling separate loss and gradient calculations as it can compute both in a single GPU kernel invocation.