Event Phone: 1-610-715-0115

Cancellation Policy: If you cancel your registration two weeks or more before the course is scheduled to begin, you are entitled to receive your choice of either a credit for a future seminar (which can be applied toward any of our courses) or a refund of the registration fee (minus a processing fee of $50). 

In the unlikely event that Statistical Horizons LLC must cancel a seminar, we will do our best to inform you as soon as possible of the cancellation. You would then have the option of receiving a full refund of the seminar fee or a credit towards another seminar. In no event shall Statistical Horizons LLC be liable for any incidental or consequential damages that you may incur because of the cancellation.

A Distinguished Speaker Series Seminar by Cynthia Rudin, Ph.D.

This three-part lecture covers three pillars of interpretable machine learning: dimension reduction for data visualization, sparse models for tabular data, and interpretable neural networks for computer vision. These are essential topics for any researcher working in high-stakes machine learning applications—and genuinely useful ones.

Part 1: Dimension Reduction for Data Visualization

Dimension reduction (DR) for data visualization provides unique insights into the structure of high-dimensional data. DR offers a bird’s-eye view of a dataset, revealing clusters and their relationships, manifolds, branching patterns, and even potential errors in the data. It is extremely effective for scientific discovery and hypothesis generation. We will discuss key elements of DR algorithms leading to the derivation of the PaCMAP algorithm, with applications in bioinformatics, name-ethnicity classification, finance, and neurology.

Part 2: Sparse Models and Rashomon Sets for Tabular Data

While the trend in machine learning has moved toward increasingly complex black-box models, such models have shown no performance advantage for many real-world tabular datasets. For these datasets, simpler models—sometimes small enough to fit on an index card—can be just as accurate and far easier to use. The challenge is that designing interpretable models is difficult due to the “interaction bottleneck,” which arises when domain experts must work closely with machine learning algorithms. We’ll review two families of interpretable models—optimal sparse decision trees and sparse generalized additive models—and introduce the Rashomon set framework as a principled approach to managing the interaction bottleneck, with examples from finance and criminal justice.

Part 3: Interpretable Neural Networks for Computer Vision

Prototype neural networks are among the most popular inherently interpretable architectures for computer vision and signal processing. These models make predictions by comparing parts of an input image to parts of prototypical images, assigning a score to each comparison and summing those scores to form the final prediction. We will discuss the ProtoPNet algorithm and its extension, ProtoConcept, in which a cluster of images defines a “concept prototype,” making comparisons richer and more informative. An application to ICU neurology is also included.

The lecture concludes with an application to computer-aided mammography, in which an interpretable neural network led to a scientific discovery: subtle left-right asymmetries in mammograms can predict breast cancer up to five years in advance. The AsymMirai algorithm was the fifth most-viewed paper in Radiology in 2024.

See also:

Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, and Chudi Zhong. “Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges.” Statistics Surveys, 2022. https://arxiv.org/abs/2103.11251