What is a F1?
A "roll-up" binary classification metric that relies on both precision and recall.
F1 explained in plain English
A "roll-up" binary classification metric that relies on both precision and recall. Here is the formula:
Suppose precision and recall have the following values: - precision = 0.6 - recall = 0.4 You calculate F1 as follows:
When precision and recall are fairly similar (as in the preceding example), F1 is close to their mean. When precision and recall differ significantly, F1 is closer to the lower value. For example: - precision = 0.9 - recall = 0.1
Example
Practitioners refer to f1 when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- AUC
A number between 0.
- BERT
A model architecture for text representation.
- MBPP
Abbreviation for Mostly Basic Python Problems.
- PR AUC
Area under the interpolated precision-recall curve, obtained by plotting (recall, precision) points for different values of the classification threshold.
- ROUGE
A family of metrics that evaluate automatic summarization and machine translation models.
- A/B testing
A statistical way of comparing two (or more) techniques—the A and the B.
- ablation
A technique for evaluating the importance of a feature or component by temporarily removing it from a model.
- accuracy
The number of correct classification predictions divided by the total number of predictions.
- activation function
A function that enables neural networks to learn nonlinear (complex) relationships between features and the label.
- active learning
A training approach in which the algorithm chooses some of the data it learns from.