47 citations · 109 across the 14 of their papers we have counts for
14 papers
Data Science with LLMs and Interpretable Models
Sebastian Bordt, Ben Lengerich, Harsha Nori +1
Recent years have seen important advances in the building of interpretable models, machine learning models that are designed to be easily understood by humans. In this work, we sho…
Interpretable Predictive Models to Understand Risk Factors for Maternal and Fetal Outcomes
Tomas M. Bosschieter, Zifei Xu, Hui Lan +5
Although most pregnancies result in a good outcome, complications are not uncommon and can be associated with serious implications for mothers and babies. Predictive modeling has t…
Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning
Jannik Deuschel, Caleb N. Ellington, Yingtao Luo +3
Interpretable policy learning seeks to estimate intelligible decision policies from observed actions; however, existing models force a tradeoff between accuracy and interpretabilit…
Estimating Discontinuous Time-Varying Risk Factors and Treatment Benefits for COVID-19 with Interpretable ML
Benjamin Lengerich, Mark E. Nunnally, Yin Aphinyanaphongs +1
Treatment protocols, disease understanding, and viral characteristics changed over the course of the COVID-19 pandemic; as a result, the risks associated with patient comorbidities…
Using Interpretable Machine Learning to Predict Maternal and Fetal Outcomes
Tomas M. Bosschieter, Zifei Xu, Hui Lan +5
Most pregnancies and births result in a good outcome, but complications are not uncommon and when they do occur, they can be associated with serious implications for mothers and ba…
Executive Function: A Contrastive Value Policy for Resampling and Relabeling Perceptions via Hindsight Summarization?
Chris Lengerich, Ben Lengerich
We develop the few-shot continual learning task from first principles and hypothesize an evolutionary motivation and mechanism of action for executive function as a contrastive val…
Ten Quick Tips for Deep Learning in Biology
Benjamin D. Lee, Anthony Gitter, Casey S. Greene +17
Machine learning is a modern approach to problem-solving and task automation. In particular, machine learning is concerned with the development and applications of algorithms that…
Dropout as a Regularizer of Interaction Effects
Benjamin Lengerich, Eric P. Xing, Rich Caruana
We examine Dropout through the perspective of interactions. This view provides a symmetry to explain Dropout: given variables, there are possible sets of va…
How Interpretable and Trustworthy are GAMs?
Chun-Hao Chang, Sarah Tan, Ben Lengerich +2
Generalized additive models (GAMs) have become a leading modelclass for interpretable machine learning. However, there are many algorithms for training GAMs, and these can learn di…
Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models
Benjamin Lengerich, Sarah Tan, Chun-Hao Chang +2
Models which estimate main effects of individual variables alongside interaction effects have an identifiability challenge: effects can be freely moved between main effects and int…
Learning Sample-Specific Models with Low-Rank Personalized Regression
Benjamin Lengerich, Bryon Aragam, Eric P. Xing
Modern applications of machine learning (ML) deal with increasingly heterogeneous datasets comprised of data collected from overlapping latent subpopulations. As a result, traditio…
Hybrid Subspace Learning for High-Dimensional Data
Micol Marchetti-Bowick, Benjamin J. Lengerich, Ankur P. Parikh +1
The high-dimensional data setting, in which p >> n, is a challenging statistical paradigm that appears in many real-world problems. In this setting, learning a compact, low-dimensi…
Towards Visual Explanations for Convolutional Neural Networks via Input Resampling
Benjamin J. Lengerich, Sandeep Konam, Eric P. Xing +2
The predictive power of neural networks often costs model interpretability. Several techniques have been developed for explaining model outputs in terms of input features; however,…
Retrofitting Distributional Embeddings to Knowledge Graphs with Functional Relations
Benjamin J. Lengerich, Andrew L. Maas, Christopher Potts
Knowledge graphs are a versatile framework to encode richly structured data relationships, but it can be challenging to combine these graphs with unstructured data. Methods for ret…