Logarithmic loss measuring the accuracy of probabilistic predictions, penalizing confident wrong predictions.
A collection of data examples used for training, validating, or testing machine learning models.
The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error.
A function that scores how wrong a model's prediction is as a single number, which training then works to make as small as possible.
Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.
A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.
A non-linear function applied to neuron outputs that introduces non-linearity, enabling networks to learn complex patterns.
A function that turns a list of scores (logits) into probabilities that are all positive and sum to 1; the standard output of classifiers and language models.
A loss function for classification that measures the difference between predicted and true probability distributions.
Logarithmic loss measuring the accuracy of probabilistic predictions, penalizing confident wrong predictions.
This concept is essential for understanding model evaluation & metrics and forms a key part of modern AI systems.