Leif Johnson

I am a Computer Science graduate student at The University of Texas at Austin. I am interested in computational models of cognitive tasks such as language learning, motor learning, and concept formation.

Contact

Email: leif@cs.utexas.edu
Desk: ENS 32NE02

Publications

Talks

Learning to Reach Using Sensorimotor Maps, Ballard/Hayhoe lab presentation, 28 Sep 2009. PDF

Conferences

E Teiniker, S Mitterdorfer, L Johnson, C Kreiner, Z Kovacs, R Weiss, "A Test-Driven Component Development Framework based on the CORBA Component Model," 27th Annual International Computer Software and Applications Conference, 2003.

Workshops

L Johnson, P Wurman, "Information and Product Quality Dynamics in Tiered Supply Networks," AAAI Workshop on Multi-Agent Modeling and Simulation of Economic Systems, 2002. PDF

Software

Most of my code these days is written in Python, often relying heavily on numpy.

python-kohonen: A collection of several vector quantizers, including self-organizing (Kohonen) map, neural gas, and growing neural gas.
python-perceptron: The classic perceptron and the voted (averaged) perceptron.
python-pursuit: The matching pursuit sparse coding algorithm, both deterministic and probabilistic flavors.
python-qdp: The quadratic-time dependency parser described by Galley and Manning in their 2009 ACL paper. Dan Garrette and I implemented the algorithm in Python and in C++; the C++ version is about 4x faster.