Rich Caruana

Removing the Genetics from the Standard Genetic Algorithm

Accurate intelligible models with pairwise interactions

Standard generalized additive models (GAMs) usually model the dependent variable as a sum of univariate models. Although previous studies have shown that standard GAMs can be in...

An empirical comparison of supervised learning algorithms

A number of supervised learning methods have been introduced in the last decade. Unfortunately, the last comprehensive empirical evaluation of supervised learning was the Statlo...

Learning Many Related Tasks at the Same Time with Backpropagation

Hinton [6] proposed that generalization in artificial neural nets should improve if nets learn to represent the domain's underlying regularities. Abu-Mustafa's...

Promoting Poor Features to Supervisors: Some Inputs Work Better as Outputs

In supervised learning there is usually a clear distinction between inputs and outputs --- inputs are what you will measure, outputs are what you will predict from those measure...

Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping

The conventional wisdom is that backprop nets with excess hidden units generalize poorly. We show that nets with excess capacity generalize well when trained with backprop and e...

Multitask Learning

Multitask Learning: A Knowledge-Based Source of Inductive Bias