Computers (in senses of machines and automatons) were originally created as the attempt to imitate human thinking processes. As a researcher in computer science, I have developed an affection toward understanding of how humans perform thinking in conceptual realm. If there is such a thing that could potentially be my current research direction, trying to understand the intuition behind human thinking model must be it.
Thought model
Simply knowing how to train neural networks does not acquaint someone with the insight into the brain. It simply creates another kind of apparatuses that is comparatively hard to understand. So I spent years to look for a more worthwhile means to understand the cognitive process of thinking. And finally after years of research, it has come to light that thinking could be modeled and creativity could be elaborated. The important of this research, is not for what I have done, but for what my model could be used.
(Yet) Another Theoretical Model of Thinking. Patrick Virie.
Virie, P. (2015). (Yet) Another Theoretical Model of Thinking. arXiv preprint arXiv:1511.02455.
Sustainable AI
In the past, a concept called "Deep learning" was found. With it, came the gift of near human intelligence, and the society of research was established, uniting the AI community in peace. Decades passed before large language model was presented. Pain and confusion flowed in its wake, and people were struggling with the fear of losing jobs. This is a story of the end time. We know this, because the semi-conductor resources are depleted. Under the dark influence of trade war, humanity must squeeze every drop from what we have. And people eyes are set upon sustainability.
Homeworld 2 parody
Learning to search
In this work, I venture into the the learning to learn paradigm using a neural network. The result is a neural network that learns to search through the given input space to find a configuration that matches the provided figure. Learning to search can be considered an alternative to learning with less data, or even one-shot learning. It does not need any variation in the training example; because the model has to search for it with the possibility to extend to multi-object classification.
Robocup small size league
I had participated in the Robocup small size league around 2006-2008 as a programmer for Plama-Z, one of the famous RoboCup small-size league teams from Thailand. My role in the team involved developing a visual feedback system and a strategy-level artificial intelligence. Our team's final match with CM-Dragon at Georgia tech, Atlanta 2007 was considered to be one of the best match in the history of SSL with the draw of the two teams during the normal play. The winner, CM-Dragon, was designated in penalty kicks.
Our team loss at that time was a drive for me to do research on how to predict ball drop positions from initial trajectory data. The result was an algorithm that allows the system to predict ball path and move the robots to intercept it in time.
Spatial conformation
Since I am not smart enough to always write a correct program for a robot, so I make a robot follows my erroneous program in a meaningful way instead.
When humans try to explain some concepts to others, the recipients may somehow be able to understand them even if the explanations are highly abstract and missing full details. I would like to apply the same idea into robotics where we are not trying to give perfect plans to machines; instead, we are going to show only the abstract, inaccurate, and incomplete versions of the plans and let the machines deduce the relations to the real scenarios by themselves. With basic intuition, the problem can be regarded as the localization problem of the current state into the abstract plans through spatial matching. I have been developing algorithms that can be used to find relation between patterns in situations and plans. Details can be found in my thesis.
Problem solving by spatial conformation. Chatavut Viriyasuthee
Master of Science, School of computer science, McGill University, November 2011.
Conformative Filter: A Probabilistic Framework for Localization in Reduced Spaces. Chatavut Viriyasuthee and Gregory Dudek.
In Proceedings of the 8th Canadian Conference on Computer and Robot Vision (CRV '11), pp. 24-31. St. John's, Newfoundland, Canada. May 2011.
One-to-one Feature Matching with Inaccurate Maps. Chatavut Viriyasuthee and Gregory Dudek.
In Proceedings of the 2011 IEEE International Conference on Robotics and Biomimetics (ROBIO 2011), Phuket, Thailand, December 2011.
Terrain Coverage
I had been participated in the terrain coverage research with Professor Ioannis Rekleitis and Mr. Anqi Xu in the Mobile Robotics lab at McGill. The goal of this research is to develop an optimal strategy for controling an agent(s) to perform area coverage in a given bounded region. I find myself interested in this research because any coverage algorithm can be applied to reinforcement learning as a policy for initial exploration.