I don’t have any funded graduate positions now. But if you are still interested in my lab, please read the following article for the research in HDILab before sending any emails.

About research in HDILab

Research

Human-Level Artificial Intelligence

A quest to program a robot that we can talk with it to ask many services like a human buttler

Publications

Journal papers (peer-reviewed)

Atom: A Grammar for Unit Visualizations

PDF Code Project Slides Video

Pre-prints

Despite recent advances in many application-specific domains, we do not know how to build a human-level artificial intelligence (HLAI). We conjecture that learning from others’ experience with the language is the essential characteristic that distinguishes human intelligence from the rest. Humans can update the action-value function with the verbal description as if they experience states, actions, and corresponding rewards sequences firsthand. In this paper, we present a classification of intelligence according to how individual agents learn and propose a definition and a test for HLAI. The main idea is that language acquisition without explicit rewards can be a sufficient test for HLAI.
arxiv, 2021

Even with impressive advances in application specific models, we still lack knowledge about how to build a model that can learn in a human-like way and do multiple tasks. To learn in a human-like way, we need to provide a diverse experience that is comparable to human’s. In this paper, we introduce our ongoing effort to build a simulated environment for developmental robotics (SEDRo). SEDRo provides diverse human experiences ranging from those of a fetus to a 12th month old. A series of simulated tests based on developmental psychology will be used to evaluate the progress of a learning model. We anticipate SEDRo to lower the cost of entry and facilitate research in the developmental robotics community.
arxiv, 2018

Recent & Upcoming Talks

Recent Posts

More Posts

We read a lot of papers. This is my standarized procedure for reading a paper such that the insight from it can be kept and spread.

CONTINUE READING

This paper presents an online autoencoder that produces non-negative sparse embedding.

CONTINUE READING

This paper defines intelligence as an agent’s ability to achieve goals in a wide range of environments. And authors present elegant mathematical formulation based on the concept of rewards and Kolmogorov complexity.

CONTINUE READING

This lecture summarizies the current challenge of Deep Learning and a few approaches by Yoshua Bengio.

CONTINUE READING

This paper presents HouseFly, which is an immersive video analytics platform where 3 years of videos from multiple camera can be shown as immersive video.

CONTINUE READING

Teaching

I taught the following courses:

  • University of Texas at Arlington
    • CS4334/5334: Introduction to Data Mining
  • University of Maryland at College Park
    • INST462: Introduction to Data Visualization

Contact

  • deokgun.park@uta.edu
  • parkduckgun
  • Engineering Research Building (ERB) Room 533, University of Texas at Arlington, Texas, 76019, USA
  • Monday 10:00 to 13:00 or email for appointment