Graduate Student
Department of Cognitive Science
Univ. of California at San Diego

Exploring Intelligence since 2004

Jump to: Publications • Research Interests • Curriculum Vitae • Personal

---

Publications, Tech Reports, & Talks

• Butko, Zhang, Cottrel, & Movellan, 2008, "Visual Saliency Model for Robot Cameras," International Conference on Robotics and Automation. [PDF] - Accepted Draft
  
  We adapted a class of visual salience algorithms to run very effeciently (much faster than real time -- 10ms per frame), and showed that these visual saliency algorithms were useful in orienting a pan-tilt robotic camera toward people. The algorithm is light-weight enough to allow for considerable post-processing on targeted regions of the image (such as facial expression recognition, etc.), and gives users interacting with the robot the impression that it is an intelligent agent, because it is looking places that are interesting to the users themselves.
  
  
• Butko & Movellan, 2007. "Learning to Learn," Sixth International Conference on Development and Learning (ICDL2007). [PDF]
  
  We used reinforcement learning to frame a "proof of concept" for "learning to learn," i.e. learning to discover the states of hidden nodes in POMDPs as quickly as possible. We showed that in a biologically plausible timeframe, an infant could learn to learn very quickly whether or not a new entity in its environment was a social agent and therefore a potential caregiver.
  
  
• Wiratanaya, Lyons, Butko, & Abe, 2007. "iMime: An Interactive Character Animation System for use in Dementia Care." Intelligent User Interfaces (IUI2007), Hawaii. [PDF]
  
  My role in this project was to use machine learning, computer vision, and reinforcement learning techniques to adapt a stimulus to be more "interesting" to an observer, by automatically observing and analyzing the user's behavior watching the stimulus.
  
  
• Butko 2007, "Generative & Discriminative Naive Bayes." Technical Report, MPLAB.UCSD-1, April, 2007. [PDF]
  
  A reference for the Discriminative Naive Bayes approach to density estimation (also known as Maximum Entropy) as well as empirical evaluations of two optimization packages using the DNB implementation as a test example.
  
  
• Butko & Triesch, 2007. "Exploring the Role of Intrinsic Plasticity for the Learning of Sensory Representations," Neurocomputing, 70(7-9):1130-1138. [PDF]
  
  A journal extension of our 2006 conference paper: In this paper, we explore a mechanism by which the brain might automatically tune itself to represent sensory input in ways that are most conducive to learning.
  
  
• Bajramovic, Mattern, Butko & Denzler, 2006. "A Comparison of Nearest Neighbor Search Algorithms for Generic Object Recognition." Advanced Concepts for Intelligent Vision Systems (Acivs 2006), Antwerp, Belgium. [PDF]
  
  In this paper, we compare different techniques for facillitating efficient learning and inference in model-free methods - classes of algorithms that learn by observation and not by assumption.
  
  
• Butko, Fasel & Movellan, 2006. "Learning about Humans During the First 6 Minutes of Life," Fifth International Conference on Development and Learning (ICDL5), Bloomington, Indiana, USA. [Talk Only]
  
  In this work, we explore possible mechanisms by which human infants (and embodied robotic agents) could learn complicated visual object categories (such as faces) with no prior experience or knowledge, and without any "teacher."
  
  
• Butko & Triesch, 2006. "Exploring the Role of Intrinsic Plasticity for the Learning of Sensory Representations," European Symposeum on Artificial Neural Networks (ESANN'06), Bruges, Belgium. [PDF]
  
  In this paper, we explore a mechanism by which the brain might automatically tune itself to represent sensory input in ways that are most conducive to learning.
  
  

---

Research Interests

My ultimate interest is the grand quest of Cognitive Engineering, Viz. How can we build machines that are as truly adaptable and intelligent as organisms?

The question of how we can define, understand, and construct intelligence has been addressed by many great minds. In the beginning, it was thought that intelligence was ultimately rooted in reason and thought. My own experience and intuition suggest that this notion should be turned around. Reason and thought do not form a core from which perception and action spring and through which they mingle; perception and action underlie and give rise to everything cognitive.

It is my belief that we can only advance AI by commiting to approaches that are ultimately rooted in pereception, action, and iteraction with an uncertain and changing world. To this end, we must be students of probability, uncertainty, dynamics, information, and prediction. To address the problems of interacting with a changing world, it is important to commit ourselves to efficient methods that sacrifice "correctness" for getting the job done in time, before the world has moved on without us. We must create theories that are robust in the face of what the world can throw at us, and we must implement those theories in the real world (or domains of similar complexity) to make sure they hold.

A model of intelligence must prove itself by doing more intelligent things in the real world than researchers have been able to achieve before.

---

Curriculum Vitae

Updated 25 January, 2008.

• Download [PDF]
  

---

Personal

Go:

Play online: KGS

KGS handle: thenjb

Current KGS Rank: 11k

Daily Problem: TsumeGo of the Day

Reference: Sensei's Library

Wikipedia entry: Go (board game)

Classical Guitar:

• Now Playing: Guardame Las Vacas / Minuet in G Minor