
On Dropout, Overfitting, and Interaction Effects in Deep Neural Networks
We examine Dropout through the perspective of interactions: learned effe...
read it

How Interpretable and Trustworthy are GAMs?
Generalized additive models (GAMs) have become a leading model class for...
read it

Neural Additive Models: Interpretable Machine Learning with Neural Nets
Deep neural networks (DNNs) are powerful blackbox predictors that have ...
read it

Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models
Recent methods for training generalized additive models (GAMs) with pair...
read it

InterpretML: A Unified Framework for Machine Learning Interpretability
InterpretML is an opensource Python package which exposes machine learn...
read it

Efficient Forward Architecture Search
We propose a neural architecture search (NAS) algorithm, Petridish, to i...
read it

Interpretability is Harder in the Multiclass Setting: Axiomatic Interpretability for Multiclass Additive Models
Generalized additive models (GAMs) are favored in many regression and bi...
read it

Transparent Model Distillation
Model distillation was originally designed to distill knowledge from a l...
read it

Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning
This is the Proceedings of NIPS 2017 Symposium on Interpretable Machine ...
read it

Detecting Bias in BlackBox Models Using Transparent Model Distillation
Blackbox risk scoring models permeate our lives, yet are typically prop...
read it

Interpretable & Explorable Approximations of Black Box Models
We propose Black Box Explanations through Transparent Approximations (BE...
read it

Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration
Predictive models deployed in the real world may assign incorrect labels...
read it

Do Deep Convolutional Nets Really Need to be Deep and Convolutional?
Yes, they do. This paper provides the first empirical demonstration that...
read it

Sparse Partially Linear Additive Models
The generalized partially linear additive model (GPLAM) is a flexible an...
read it

Do Deep Nets Really Need to be Deep?
Currently, deep neural networks are the state of the art on problems suc...
read it

Using Multiple Samples to Learn Mixture Models
In the mixture models problem it is assumed that there are K distributio...
read it
Rich Caruana
is this you? claim profile