Rich Caruana

is this you? claim profile

0 followers
Microsoft

On Dropout, Overfitting, and Interaction Effects in Deep Neural Networks

We examine Dropout through the perspective of interactions: learned effe...
07/02/2020 ∙ by Benjamin Lengerich, et al. ∙ 0 ∙ share

read it
How Interpretable and Trustworthy are GAMs?

Generalized additive models (GAMs) have become a leading model class for...
06/11/2020 ∙ by Chun-Hao Chang, et al. ∙ 0 ∙ share

read it
Neural Additive Models: Interpretable Machine Learning with Neural Nets

Deep neural networks (DNNs) are powerful black-box predictors that have ...
04/29/2020 ∙ by Rishabh Agarwal, et al. ∙ 11 ∙ share

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...
11/12/2019 ∙ by Benjamin Lengerich, et al. ∙ 0 ∙ share

read it
InterpretML: A Unified Framework for Machine Learning Interpretability

InterpretML is an open-source Python package which exposes machine learn...
09/19/2019 ∙ by Harsha Nori, et al. ∙ 0 ∙ share

read it
Efficient Forward Architecture Search

We propose a neural architecture search (NAS) algorithm, Petridish, to i...
05/31/2019 ∙ by Hanzhang Hu, et al. ∙ 4 ∙ share

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...
10/22/2018 ∙ by Xuezhou Zhang, et al. ∙ 0 ∙ share

read it
Transparent Model Distillation

Model distillation was originally designed to distill knowledge from a l...
01/26/2018 ∙ by Sarah Tan, et al. ∙ 0 ∙ share

read it
Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning

This is the Proceedings of NIPS 2017 Symposium on Interpretable Machine ...
11/27/2017 ∙ by Andrew Gordon Wilson, et al. ∙ 0 ∙ share

read it
Detecting Bias in Black-Box Models Using Transparent Model Distillation

Black-box risk scoring models permeate our lives, yet are typically prop...
10/17/2017 ∙ by Sarah Tan, et al. ∙ 0 ∙ share

read it
Interpretable & Explorable Approximations of Black Box Models

We propose Black Box Explanations through Transparent Approximations (BE...
07/04/2017 ∙ by Himabindu Lakkaraju, et al. ∙ 0 ∙ share

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...
10/28/2016 ∙ by Himabindu Lakkaraju, et al. ∙ 0 ∙ share

read it
Do Deep Convolutional Nets Really Need to be Deep and Convolutional?

Yes, they do. This paper provides the first empirical demonstration that...
03/17/2016 ∙ by Gregor Urban, et al. ∙ 0 ∙ share

read it
Sparse Partially Linear Additive Models

The generalized partially linear additive model (GPLAM) is a flexible an...
07/17/2014 ∙ by Yin Lou, et al. ∙ 0 ∙ share

read it
Do Deep Nets Really Need to be Deep?

Currently, deep neural networks are the state of the art on problems suc...
12/21/2013 ∙ by Lei Jimmy Ba, et al. ∙ 0 ∙ share

read it
Using Multiple Samples to Learn Mixture Models

In the mixture models problem it is assumed that there are K distributio...
11/28/2013 ∙ by Jason D. Lee, et al. ∙ 0 ∙ share

read it

Rich Caruana

Featured Co-authors

Eric P Xing

Jure Leskovec

Jason D. Lee

Andrew Gordon Wilson

John Langford

Eric Horvitz

Jason Yosinski

Jacob Bien

Giles Hooker

Ece Kamar

Anna Goldenberg

On Dropout, Overfitting, and Interaction Effects in Deep Neural Networks

How Interpretable and Trustworthy are GAMs?

Neural Additive Models: Interpretable Machine Learning with Neural Nets

Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models

InterpretML: A Unified Framework for Machine Learning Interpretability

Efficient Forward Architecture Search

Interpretability is Harder in the Multiclass Setting: Axiomatic Interpretability for Multiclass Additive Models

Transparent Model Distillation

Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning

Detecting Bias in Black-Box Models Using Transparent Model Distillation

Interpretable & Explorable Approximations of Black Box Models

Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration

Do Deep Convolutional Nets Really Need to be Deep and Convolutional?

Sparse Partially Linear Additive Models

Do Deep Nets Really Need to be Deep?

Using Multiple Samples to Learn Mixture Models