Paul Utgoff - In Memoriam (1951 - 2008)


Contact Information

Paul Utgoff directs the Machine Learning Laboratory in the College of Information & Computer Sciences at the University of Massachusetts at Amherst.

Research Focus

My main research interests are rooted in the longstanding fundamental problem of how intelligent systems can acquire features, terms, and other representational structures that are prerequisite to further learning. Simple learning can be accomplished by application of a statistical pattern-finding algorithms, but how are learned patterns employed in the grander design of sustained learning over the lifetime of an intelligent entity? In terms of Clark & Thornton's compelling distinction between Type-1 and Type-2 learning, I am completely intrigued with the issues involved in understanding and modeling Type-2 learning, which involves building representational mappings when no statistical relationship exists between the independent and dependent variables. Quartz has also described well this dichotomy between setting up representations (Type-2) and then making use of those representations for the better understood processes of identifying simple input/output mappings (Type-1). What mechanisms can account for sustained Type-2 and Type-1 learning? For me, this is the most exciting and most central problem in attaining new levels of mechanical intelligence.

I have been working on algorithms that incidentally solve Type-1 problems when present and possible, each one producing a building block that joins a many-layered deeply-nested organization of such elements. Earlier learning lays the groundwork for later learning. I am guided by the principle that all learning is simple if the prerequisites are in place. I am quite fascinated by textbooks, as each presents a large body of coherent knowledge carefully organized in terms of building blocks and their dependencies.

Present Students

I am ably assisted by my graduates students:

Classification of Phytoplankton Images

UMass researchers from the Computer Vision Laboaratory and the Machine Learning Laboratory are collaborating with marine scientists from Bigelow Laboratory to build image classification systems that are capable of discriminating a large variety of phytoplankton. The ability to automate analyses of samples in various settings will enable studies of such ocean life to be conducted at much lower cost, and in a much more timely manner. We are investigating classification algorithms, ensemble classifiers, and feature sets that enable separation of useful classes to apply to challenging real-world problems.

Music Perception

I am collaborating on automated music perception with Prof. Chris Raphael of our Mathematics and Statistics Department. Ideally, we would like to be able to take as input an audio signal of a music performance, and produce as output a music score for the selection that was performed. There are many subproblems, including determining the fundamental pitch events, pulse, meter, key signature, intentional variations of pitch and note duration, articulation identification, voice leading and chord identification. We approach many of these problems starting with a midi performance instead of an audio signal, to factor out the problem of correctly identifying pitch events. If these kinds of problems interest you, and you have studied music performance, come get involved.

Decision Tree Induction

I have developed and I maintain the ITI (Incremental Tree Inducer) and DMTI (Direct Metric Tree Induction) decision tree induction systems. I welcome questions, suggestions, and hearing of useful applications.

Ph.D. Graduates


Last Updated: June 10, 2004
Paul Utgoff:
© Copyright 2004, All Rights Reserved, Paul Utgoff, University of Massachusetts