Articles tagged with MachineLearning


Binary CrossEntropy Loss
Binary CrossEntropy (BCE), also known as log loss, is a loss function used in binary or multilabel machine learning training.
It's nearly identical to Negative …


Categorical CrossEntropy Loss
Categorical CrossEntropy Loss Function, also known as Softmax Loss, is a loss function used in multiclass classification model training. It applies the Softmax Activation Function …

Negative LogLikelihood
Negative loglikelihood is a loss function used in multiclass classification.
Calculated as $log(\textbf{y})$, where $\mathbf{\text{y \u2026}}$

Softmax Activation Function
The Softmax function converts a vector of numbers into a vector of probabilities that sum to 1. It's applied to a model's outputs (or Logits …

Sigmoid Activation Function
The Sigmoid function squeezes numbers into a probabilitylike range between 0 and 1.^{1} Used in Binary Classification model architectures to compute loss on discrete …


Outofdomain data
When data is provided to a model that is significantly different from what it was trained on, it's referred to as outofdomain data.

Mean Absolute Difference  L1 Loss
Mean Absolute Difference (MAE) is a function for assessing Regression predictions. It's also as L1 Loss because it takes the L1 Norm of the error …