Kee Siong's Homepage

Kee Siong Ng
Adjunct Research Fellow,
Computer Sciences Laboratory,
College of Engineering and Computer Science,
The Australian National University.
keesiong dot ng at gmail dot com

Brief Bio

I am originally from a small town called Muar in Malaysia. I came to Australia in 1998 to study and have been here since.
I studied symbolic machine learning under Prof John Lloyd at the ANU for my PhD and subsequently did a postdoc with
Dr Peter Cheeseman and Dr William Uther at NICTA. I am currently involved in several aspects of artificial intelligence
research, including a joint attempt with Joel Veness at approximating Dr Marcus Hutter's AIXI agent.

I also have three US$2.56 cheques from Prof Don Knuth. :)

Professional Interests

Integrating logic and probability
Symbolic or knowledge-based machine learning
Functional and logic programming paradigms
Automated theorem proving in higher-order logics
Uncertainty modelling in AI
Universal reinforcement learning
Semantic sequence prediction and data compression
Computational learning theory
Literate programming

Publications

Journal papers

A Monte Carlo AIXI Approximation
J. Veness, K.S. Ng, M. Hutter, D. Silver, 2009, arXiv:0909.0801, Under review. (42 pages)
Declarative Programming for Agent Applications
J.W. Lloyd, K.S. Ng, 2009, Under review. (42 pages)
Probabilistic Modelling, Inference and Learning using Logical Theories
K.S. Ng, J.W. Lloyd, W.T.B. Uther, Annals of Mathematics and Artificial Intelligence, vol 54(1), pp. 159-205, 2008.
Probabilistic Reasoning in a Classical Logic
K.S. Ng, J.W. Lloyd, Journal of Applied Logic, vol 7, pp. 218-238, 2009.

Conference/Workshop papers

Probabilistic and Logical Beliefs
J.W. Lloyd, K.S. Ng, In M. Dastani et al (Eds), LADS 2007, LNAI 5118, pp. 19-36, 2008.
Reflections on Agent Beliefs
J.W. Lloyd, K.S. Ng, In M. Baldoni et al (Eds), DALT 2007, LNCS 4897, pp. 122-139, 2007.
Learning Modal Theories
J.W. Lloyd, K.S. Ng, In S. Muggleton, R. Otero and A. Tamaddoni-Nezhad (Eds.): ILP 2006, LNAI 4455, pp. 320-334, 2007.
- This paper presents a general framework for learning theories in a higher-order multi-modal logic.
(Agnostic) PAC Learning Concepts in Higher-order Logic, (A longer preprint.)
K.S. Ng, In J. Furnkranz, T. Scheffer and M. Spiliopoulou (Eds.): ECML 2006, LNAI 4212, pp. 711-718, 2006.
- This paper studies the PAC and agnostic PAC learnability of some function classes expressible in higher-order logic.
Generalization Behaviour of Alkemic Decision Trees,
K.S. Ng, In S. Kramer and B. Pfahringer (Eds.): ILP 2005, LNAI 3625, pp. 246-263, 2005.
- This paper studies the VC dimensions of some common function classes defined on structured data, including sets, multisets, trees, graphs, etc.
Predicate Selection for Structural Decision Trees, Additional notes
K.S. Ng, J.W. Lloyd, In S. Kramer and B. Pfahringer (Eds.): ILP 2005, LNAI 3625, pp. 264-278, 2005.
- This paper gives efficient algorithms for the problem of picking from a structured search space a predicate that partitions a set of examples well.
Personalisation for User Agents
J.J.Cole, M.Gray, J.W. Lloyd, K.S. Ng, In Proceedings of the 4th International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS-05), pp. 603-610, 2005.
- This paper presents a symbolic machine learning framework for achieving personalisation in intelligent user agents.
Symbolic Learning for Adaptive Agents
J.J. Cole, J.W. Lloyd, K.S. Ng, Proceedings of the Annual Partner Conference, Smart Internet Technology Cooperative Research Centre, pp 139--148, 2003
- This paper presents an interesting new perspective on relational reinforcement learning.
Predictive Toxicology using a Decision-tree Learner
K.S. Ng, J.W. Lloyd, A.W. Slater, The 2000-1 Predictive Toxicology Challenge Workshop, 5th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD-01), 2001

Theses

Learning Comprehensible Theories from Structured Data,
K.S. Ng, PhD Thesis, The Australian National University, 2005. (postscript version)
Neural Networks for Structured Data
K.S. Ng, Honours Thesis, 2001

Miscellaneous

Modal Functional Logic Programming
J.W. Lloyd, K.S. Ng, J.W. Veness, Tech Report, 2007
Agnostic PAC Learning Decision Lists is Hard
K.S. Ng, 2005

Project Proposals

Towards General Machine Intelligence, K.S. Ng, July 2009.
Architectures for Intelligent Agents, K.S. Ng, W. Uther, B. Hengst, Sep 2007

Softwares

Download the latest version of Alkemy. (Escher is now incorported into Alkemy!!)

This is the manual for Alkemy.
A Tutorial Introduction to Alkemy K.S. Ng, 2006
This is the Alkemy literate program.
The Alkemy Source Book K.S. Ng, 2009, 258 pages.

Download the latest version of Escher!

This is the Escher literate program.
An Implementation of Escher K.S. Ng, 2006.

The Godel programming language can be found here.

I'm currently working on Bach. This is a work-in-progress, but a version of the system is available for experimentation on request.
Here's the literate program An Implementation of Bach.

Community Service

Co-organiser of a NIPS-2009 mini symposium on Partially Observable Reinforcement Learning
PC Member for 2009 International Workshop on Statistical Relational Learning (SRL-09)
PC Member for 2006 European Conference on Machine Learning (ECML-06)

Datasets and Useful Documents

Molecular structures for the 2000-1 Predictive Toxicology Challenge