Apple ML Researchers Develop 'Neo': A Visual Analytics System That Enables Machine Learning Practitioners To Generalize Confusion Matrix Visualization to Hierarchical and Multi-Output Labels

In Machine Learning (ML), model evaluation is the most challenging step. The confusion matrix is one of the globally utilized performance metrics to evaluate the model for classification tasks. It is also a visualization tool that many ML courses and researchers have used. Moreover, it is a table with two dimensions, i.e., actual class label and predicted class label. The actual class label is represented by a row, while a column in the confusion matrix represents the predicted class label.