AMIL is an integrated set of Java code for learning probabilistic models for Multiple Instance (MI) classification problems. It implements basic data structures for managing bags and instances, data read/write methods, and a general framework for learning probabilistic classifiers based on a generalization of Diverse Density (Maron & Lozano-Perez, NIPS 1998) including MI Logistic Regression (Ray & Craven, ICML 2005). Additionally, it implements instance-query selection strategies for MI Active Learning and modifications to the training algorithm to learn from labels at multiple levels of granularity (Settles et al., NIPS 2008).
The AMIL Java software library can downloaded here: amil-0.1.tar.gz.
© 2007 by Burr Settles. It is provided "as is," with no representations or warranties of any kind. This is version 0.1, released open-source via the GPL Version 3. Be sure to read and, if appropriate, cite the paper:
B. Settles, M. Craven, and S. Ray (2008). Multiple Instance Active Learning. Advances in Neural Information Processing Systems (NIPS), 20, 1289-1296. MIT Press.
Here's a BibTeX entry if you dig that sort of thing:
@incollection{settles.nips08,
Author = {B. Settles and M. Craven and S. Ray},
Booktitle = {Advances in Neural Information Processing Systems (NIPS)},
Pages = {1289--1296},
Publisher = {MIT Press},
Title = {Multiple-Instance Active Learning},
Volume = {20},
Year = {2008}}