Australasian Conference on Artificial Intelligence 2015

12 papers
The 2015 Australasian Conference on Artificial Intelligence featured research across several domains, including algorithmic analysis, data mining, and multi-agent systems. A notable focus was placed on the theoretical comparison of search algorithms, specifically examining the selection between Breadth-First Search (BFS) and Depth-First Search (DFS) in both tree and graph search contexts. Other research directions included the discovery of causal structures from time series data using enhanced Granger causality and the application of data mining techniques to analyze complications in cancer treatment. Methodological contributions involved stable feature selection using Support Vector Machines (SVM) and decentralized multi-agent approaches for voltage regulation in power systems. Prolific contributors to this edition included researchers such as Marcus Hutter, Tom Everitt, Dinh Q. Phung, and Svetha Venkatesh. The collected works reflected a balance between fundamental algorithmic studies and applied machine learning in fields such as healthcare and engineering.

Top Authors

AuthorPapers
Chao Yu2
Dinh Phung2
Marcus Hutter2
Svetha Venkatesh2
Tom Everitt2
Dang Nguyen1
Fang Chen1
Fenghui Ren1
Hongtao Lv1
Jianye HAO1
Ling Luo1
Mohan Sridharan1
Peter Vamplew1
Sunil Gupta1
Yun Sing Koh1

Papers

Title
A Dual Network for Transfer Learning with Spike Train Data
A Multi-Agent Approach for Decentralized Voltage Regulation by Considering Distributed Generators
Analytical Results on the BFS vs. DFS Algorithm Selection Problem: Part II: Graph Search
Analytical Results on the BFS vs. DFS Algorithm Selection Problem. Part I: Tree Search
Discovering Causal Structures from Time Series Data via Enhanced Granger Causality
Hierarchical Learning for Emergence of Social Norms in Networked Multiagent Systems
Modeling Ice Storm Climatology
Possibilistic Inferences in Answer Set Programming
Reinforcement Learning of Pareto-Optimal Multiobjective Policies Using Steering
Stable Feature Selection with Support Vector Machines
Tracking Drift Severity in Data Streams
Understanding Toxicities and Complications of Cancer Treatment: A Data Mining Approach