Leif Johnson

• Home
• Contact
• Publications
• Software
• Education
• Industry
• Etc

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. I do a lot of sparse / efficient coding to try to uncover possible relationships between sensory and motor codes for cognitive domains. I'm also interested in how these codes interact with unsupervised or minimally supervised techniques for learning control policies.

Contact

Email: leif@cs.utexas.edu
Desk: GDC 3.518B

Publications

2013

• L Johnson, J Cooper, D Ballard. "Unified loss functions for multi-modal pose regression." In Proc. IEEE International Joint Conference on Neural Networks. PDF
• L Johnson, B Sullivan, D Ballard, M Hayhoe. "A soft barrier model for human behavior in a two-task driving environment." In Proc. Annual Meeting of the Cognitive Science Society. PDF
• L Johnson. "Python tools for coding and feature learning." Talk given at SciPy 2013. slides video

2012

• P Jyothi, L Johnson, C Chelba, B Strope. "Distributed discriminative language models for Google voice-search." In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing. PDF
• P Jyothi, L Johnson, C Chelba, B Strope. "Large-scale discriminative language model reranking for voice-search." In Proc. North American Association for Computational Linguistics - Human Language Technologies. PDF
• R Miikkulainen, E Feasley, L Johnson, I Karpov, P Rajagopalan, A Rawal, W Tansey. "Multiagent Learning through Neuroevolution." In J. Liu et al., eds., Advances in Computational Intelligence, LNCS 7311, 24-46, Berlin, Heidelberg: Springer. PDF
• B Sullivan, L Johnson, C Rothkopf, M Hayhoe, D Ballard. "The effect of uncertainty and reward on fixation behavior in a driving task." Journal of Vision 12 (9). DOI 10.1167/12.13.19. PDF

2011

• B Sullivan, L Johnson, D Ballard, M Hayhoe. "A modular reinforcement learning model for human visuomotor behavior in a driving task." In Proc. Active Vision Symposium, Artificial Intelligence and the Study of Behavior. PDF

2003

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

2002

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

See my full profile on Google Scholar.

Software

Most of my code these days is written in Python, with a lot of help from the amazing scipy. Recently I've also been using the fantastic Theano tool for defining and optimizing cost functions.

• py-c3d: A small set of utilities—at this point consisting of a file reader and writer, and a simple OpenGL visualization tool—for dealing with motion capture data files in the C3D binary format.
• python-depparse: A Python library and command-line tool for non-projective dependency parsing of natural language text.
• py-grep-plot: A command-line tool for creating quick plots from data in text files.
• py-kohonen: A collection of several vector quantizers, including self-organizing (Kohonen) map, neural gas, and growing neural gas.
• py-lars: A naive implementation of Least Angle Regression, plus an implementation of Mairal et al.'s 2009 ICML paper on dictionary learning for sparse coding. You really ought to use their amazing C++ implementation with Python (and Matlab) bindings.
• py-particle: A Python implementation of a generic particle filter.
• py-perceptron: The classic perceptron and the averaged perceptron (an approximation to the voted perceptron).
• py-pursuit: The matching pursuit sparse coding algorithm, and an implementation of the convolutional sparse coding approach described by Smith & Lewicki (2006). Includes an experimental CUDA implementation !
• py-rbm: Several types of Restricted Boltzmann Machines. Also see theano-nets for neural network implementations using Theano.
• py-sound: A collection of code for representing and manipulating sound data.
• py-trm: A Python wrapper for the Gnuspeech Tube Resonance Model, a vocal synthesizer.

Education

Industry

Etc

Among other things, I like pie and sitting on porches. See Leif Johnson for my personal site.