9th IFIP International Conference On Intelligent Information Processing
18-21, November, 2016，Melbourne, Australia
The IIP conference series provides a forum for engineers and scientists in academia, university and industry to present their latest research findings in any aspects of intelligent information processing. IIP2016 attempts to meet the needs of a large and diverse community.
International Federation for Information Processing, IFIP TC12
Chinese Association for Artificial Intelligence
Institute of Computing Technology, Chinese Academy of Sciences
E. Chang (Australia)
Z. Shi (China) S. Vadera (UK) G. Li (Australia)
Automated Reasoning and Cognitive Computing
University of Koblenz
Abstract: This talk discusses the use of first order automated reasoning in question answering and cognitive computing. The history of automated reasoning systems and the state of the art are sketched. In a first part of the talk the natural language question answering project LogAnswer is briefly depicted and the challenges faced therein are addressed. This includes a treatment of query relaxation, web-services, large knowledge bases and co-operative answering. In a second part a bridge to human reasoning as it is investigated in cognitive psychology is constructed; some examples from human reasoning are discussed together with possible logical models. Finally the topic of benchmark problems in commonsense reasoning is presented together with our approach.
An Elastic, On-Demand, Data Supply Chain for Human Centred Information Dominance
The University of New South Wales, Australia
Abstract: We consider different instances of this broad framework, which can roughly be classified into two cases. In one instance, the system is assumed to be a black box, whose inner working is not known, but whose states can be (partially) observed during a run of the system. In the second instance, one has (partial) knowledge about the inner working of the system, which provides information on which runs of the system are possible. In this talk, we will review some of our recent research that investigates different instances of this general framework of ontology-based monitoring of dynamic systems. Getting the right data from any data sources, in any formats, with different sizes and have different multitudes of complexity, in real time to the right person at the right time and in a form which they can rapidly assimilate and use is the concept of Elastic On-demand Data Supply Chain. Finding out what data is needed from which system, where and why is it needed, how is the data searched, extracted, aggregated represented and how should it be presented visually so that the user can use and operate the information without much training is applying a human centred approach to on-demand data supply chain. Information Dominance represents how by using guided analytics and self-service on the data, human cognitive information capabilities including optimization of systems and resources for decision making in the dynamic and complex environment are built. In this presentation, I explain these concepts and demonstrate how the effectiveness and efficiency of the above integrated approach is validated by providing both theoretical concept proofing with stratification, target sets, reachability, incremental enlargement principle and practical concept proofing through implementation of the Faceplate. The project is funded by Australian Department of Defense.
Online learning with trapezoidal data stream
University of Technology Sydney, Australia
Abstract: An increasing number of applications on doubly-streaming data where both data volume and data dimensions increase with time have been witnessed recently. For example, in graph node classification, both the number of graph nodes and the node features, the ego-network structure of a node, often change dynamically. And in text classification, both the number of documents and text vocabulary increase over time. In this invited talk, the new problem of continuous learning from doubly-streaming data will be discussed. The problem is challenging because both data volume and data dimension increase over time. Existing online learning, online feature selection, and streaming feature selection algorithms are inapplicable. A new Online Learning with Streaming Features algorithm (OLSF for short) and its two variants that combine online learning and streaming feature selection will be introduced to show how to learn from trapezoidal data streams with infinite training instances and features.
Why is my Entity Typical or Special? Approaches for Inlying and Outlying Aspects Mining
Department of Computing and Information Systems
The University of Melbourne, Australia
Abstract: When investigating an individual entity, we may wish to identify aspects in which it is usual or unusual compared to other entities. We refer to this as the inlying/outlying aspects mining problem and it is important for comparative analysis and answering questions such as "How is this entity special?" or "How does it coincide or differ from other entities?” Such information could be useful in a disease diagnosis setting (where the individual is a patient) or in an educational setting (where the individual is a student). We examine possible algorithmic approaches to this task and investigate the scalability and effectiveness of these different approaches. firstname.lastname@example.org
Advanced Reasoning Services for Description Logic Ontologies
School of Information Technology
Griffith University, Australia
bstract: Ontology-like knowledge bases (KBs) have become a promising modeling tool in a wide variety of applications such as intelligent Web search, question understanding, in-context advertising, social media mining, and biomedicine. Such KBs are distinct from traditional KBs in that they are based on ontologies (as schemas) that assist in organization and access of information on the Web and from other sources. However, practical ontology-like KBs are usually associated with data of large volume, dynamic with content, and updated rapidly. Efficient systems have been developed for standard reasoning and query answering for OWL/Description Logic (DL) ontologies. In recent years, the issue of facilitating advanced reasoning services is receiving extensive attention in the research community. In this talk, we will discuss recent research results and challenges of three important reasoning tasks of ontologies including ontology change, query explanation and rule-based reasoning for OWL/DL ontologies.
Key Laboratory of Intelligent Information Processing
Institute of Computing Technology, Chinese Academy of Sciences
Beijing 100190, China
Abstract: Human-level artificial intelligence, which makes machines with intelligent behavior of the human brain, is the most challenging major scientific issues of this century, but also is the current hot topics in academic and industry area. Brain-like computing has become the leading edge technology in twen-ty-first Century, many countries have started the brain science and cognitive computing projects. Intelligence science has brought a number of inspiration to the machine intelligence, and promote the research on brain science, cognitive science, intelligent computing technology and intelligent robot. In this talk, I will focus on the research progress and development trend of cognitive models, brain-machine collaboration, and brain-like intelligence.
Brain-like intelligence is a new trend of artificial intelligence that aims at human-level artificial intelligence through modeling the cognitive brain and obtaining inspiration from it to power new generation intelligent systems. In recent years, the upsurges of brain science and intelligent technology research have been developed in worldwide.