GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions (2020-03-16T00:00:00.000000Z)

TL;DR

Numerical experiments show that the proposed explainable GAMI-Net enjoys superior interpretability while maintaining competitive prediction accuracy in comparison to the explainable boosting machine and other benchmark machine learning models.

Authors

Zebin Yang

1 papers

Aijun Zhang

1 papers

A. Sudjianto

1 papers

TL;DR

Authors

References52 items

How Interpretable and Trustworthy are GAMs?

Neural Additive Models: Interpretable Machine Learning with Neural Nets

From local explanations to global understanding with explainable AI for trees

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

InterpretML: A Unified Framework for Machine Learning Interpretability

Definitions, methods, and applications in interpretable machine learning

Enhancing Explainability of Neural Networks Through Architecture Constraints

Adversarial Attack Type I: Cheat Classifiers by Significant Changes

Techniques for interpretable machine learning

Explainable Neural Networks based on Additive Index Models

Explaining Explanations: An Overview of Interpretability of Machine Learning

pyGAM: Generalized Additive Models in Python

Adversarial Examples: Attacks and Defenses for Deep Learning

One Pixel Attack for Fooling Deep Neural Networks

A Unified Approach to Interpreting Model Predictions

Detecting Statistical Interactions from Neural Network Weights

“Why Should I Trust You?”: Explaining the Predictions of Any Classifier

Evaluating the Visualization of What a Deep Neural Network Has Learned

Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission

Adam: A Method for Stochastic Optimization

Exact solutions to the nonlinear dynamics of learning in deep linear neural networks

Accurate intelligible models with pairwise interactions

Intelligible models for classification and regression

A LASSO FOR HIERARCHICAL INTERACTIONS.

Variable Selection With the Strong Heredity Constraint and Its Oracle Property

Structured variable selection and estimation

PREDICTIVE LEARNING VIA RULE ENSEMBLES

Sparse additive models

Additive Groves of Regression Trees

Generalized Functional ANOVA Diagnostics for High-Dimensional Functions of Dependent Variables

A Bayesian Approach to the Design and Analysis of Fractionated Experiments

Regularities in data from factorial experiments

The elements of statistical learning: data mining, inference and prediction

Discovering additive structure in black box functions

The Elements of Statistical Learning: Data Mining, Inference, and Prediction

Generalized Linear Models

Greedy function approximation: A gradient boosting machine.

Simple Incorporation of Interactions into Additive Models

Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates

The Selection of Terms in Response-Surface Models—How Strong is the Weak-Heredity Principle?

Bayesian variable selection with related predictors

Regression modeling in back-propagation and projection pursuit learning

Approximation capabilities of multilayer feedforward networks

Hierarchical Variable Selection in Polynomial Regression Models

Projection Pursuit Regression

Definitions

Interpretable machine learning: definitions, methods, and applications

Interpretable machine learning: A guide for making black box models explainable, E-book at https://christophm

Author ' s personal copy A Fast Quartet tree heuristic for hierarchical clustering

The Elements of Statistical Learning: Data Mining, Inference, and Prediction

Select at most K pairwise interactions for training and then prune the trivial pairwise interactions according to their contributions and validation performance

Obtain the prediction residuals from the main eﬀect training stage

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names