L2Loss#

class L2Loss[source]#

Bases: Loss

This class computes the L2 loss (i.e. squared error) for each sample as:

\[\text{L2Loss}(predict, target) = \sum_{i=0}^{N_{\text{elements}}} (predict_i - target_i)^2.\]

Methods

evaluate(predict, target)[source]#

An abstract method for evaluating the loss function. Inputs are expected in a shape of (N, *). Where N is a number of samples. Loss is computed for each sample individually.

প্যারামিটার:
  • predict (ndarray) -- an array of predicted values using the model.

  • target (ndarray) -- an array of the true values.

রিটার্নস:

An array with values of the loss function of the shape (N, 1).

রেইজেস:

QiskitMachineLearningError -- shapes of predict and target do not match

রিটার্ন টাইপ:

ndarray

gradient(predict, target)[source]#

An abstract method for computing the gradient. Inputs are expected in a shape of (N, *). Where N is a number of samples. Gradient is computed for each sample individually.

প্যারামিটার:
  • predict (ndarray) -- an array of predicted values using the model.

  • target (ndarray) -- an array of the true values.

রিটার্নস:

An array with gradient values of the shape (N, *). The output shape depends on the loss function.

রেইজেস:

QiskitMachineLearningError -- shapes of predict and target do not match.

রিটার্ন টাইপ:

ndarray