Why meta-data matters?
What information is useful when designing your classifier? This video shows how meta-data helps you to improve not only the classifier performances, but also your understanding.
Draw your classifier by hand!
Sometimes it is easier to draw a classifier by hand then to train it. perClass offers you an interactive tool to draw classifiers directly in the scatter plot. You can make the decision boundary exactly as you wish!
Interactive thresholding
How to interactively build a classifier by thresholding one feature. The sdfeatplot comand enables us to inspect the class distribution for each feature. We can manually select a threshold and create a simple classifier with a mouse click.
Training classifiers from multiple images
How to efficiently work with subsets of large hyperspectral images, paint labels and combine data from multiple images for training robust classifiers.
Run your classifiers out-of-Matlab
How to transfer a Matlab prototype classifier into your product? PRSD Studio provides comprehensive support for execution of classifiers in custom applications. This video shows few examples of classifier deployment.
Live feature distributions in scatter plots
Interactive scatter plot sdscatter allows you to show live feature distributions. This helps in understanding the overlap conditions in large data sets.
Easy class subset with regular expressions
Quickly selecting subsets of classes helps you to inspect and learn from your data. PRSD Studio introduces a new, simpler way of selecting classes using regular expressions. Regular expression is a string describing a pattern matched to the class list. The simplest use is to select classes using a substring. In this video you will learn how to use regular expressions directly in the scatterplot, or while relabeling the data or creating a subset from the command line.
Understanding outliers with interactive scatter
To develop an intuitive feeling of what might work for our problem, it is important to understand our data. In this short video we show how simple interactive tools help us understand what causes the outliers and how we can easily remove them.
Interactive scatter: Work with multiple features
This short video shows how to flip through the features with cursor keys, and directly jump to a chosen feature with the context menu.
Interactive scatter: Leverage multiple sets of labels
This short video shows how to use multiple sets of labels (patients, objects, sub-classes), and to quickly switch between labels sets to understand your problem.