Showing posts with label artificial intelligence. Show all posts
Showing posts with label artificial intelligence. Show all posts

Monday, August 26, 2013

Call for Papers Uncertain Reasoning Conference-Artificial Intelligence



Call for Papers Uncertain Reasoning Conference-Artificial Intelligence

Submission Deadline: November 18th, 2013


Many problems in AI (in reasoning, planning, learning, perception and robotics) require the agent to operate with incomplete or uncertain information. The objective of this track is to present and discuss a broad and diverse range of current work on uncertain reasoning, including theoretical and applied research based on different paradigms. We hope that the variety and richness of this track will help to promote cross fertilization among the different approaches for uncertain reasoning, and in this way foster the development of new ideas and paradigms.

The Special Track on Uncertain Reasoning (UR) is the oldest track in FLAIRS conferences, running annually since 1996. The UR'2014 Special Track at the 27th International Florida Artificial Intelligence Research Society Conference (FLAIRS-27) is the 19th in the series. As the past tracks, UR'2014 seeks to bring together researchers working on broad issues related to reasoning under uncertainty.

Papers on all aspects of uncertain reasoning are invited. Papers of particular interest include, but are not limited to: 

- Uncertain reasoning formalisms, calculi and methodologies
- Reasoning with probability, possibility, fuzzy logic, belief function, vagueness, granularity, rough sets, and probability logics
- Modeling and reasoning using imprecise and indeterminate information, such as: Choquet capacities, comparative orderings, convex sets of measures, and interval-valued probabilities
- Exact, approximate and qualitative uncertain reasoning
- Bayesian networks
- Graphical models of uncertainty
- Multi-agent uncertain reasoning and decision making
- Decision-theoretic planning and Markov decision process
- Temporal reasoning and uncertainty
- Nonmonotonic reasoning
- Conditional Logics
- Argumentation
- Belief change and Merging
- Similarity-based reasoning
- Construction of models from elicitation, data mining and knowledge discovery
- Uncertain reasoning in information retrieval, filtering, fusion, diagnosis, prediction, situation assessment
- Practical applications of uncertain reasoning


All accepted papers will be published as FLAIRS proceedings by AAAI Press. We anticipate that, as in previous years, the International Journal of Approximate Reasoning (IJAR) will publish a special issue devoted to extended versions of the top papers at the track.


The proceedings of FLAIRS-27 will be published by the AAAI. Authors of accepted papers will be required to sign a form transferring copyright of their contribution to AAAI.


At least one author of each accepted paper is required to register, attend, and present the paper at FLAIRS-27.

Wednesday, July 24, 2013

Scientists Invent the Thinking Microprocessor


Scientists from the University of Zurich, ETH Zurich and partners in Germany and the U.S. have developed a microchip that processes much like the human brain. Unlike clunky predecessors that react only to environmental stimuli these new chips use neurons that will use analytic abilities, decision-making capabilities, as well as short-term memories to react to their environment in real time. 

The key to this discovering is that it can take sensations from the environment like humans and process them to make quick paced decisions. As the machine picks up on environmental cues it is capable of processing the multiple sensations to make meaning out of these cues and in term devise a type of strategy and change or adjust its course of action. It works fundamentally the say way the human brain works. 

The science of neuroinformatics typically seeks to recreate artificial bundles of nerves on supercomputers in an attempt to determine how information is processed in much the same way as the human brain processes information. The field of neuroinformatics uses mathematical models, tools, and other systems to try and mimic the neuroscientific aspects of the human nervous system. 

You may ask yourself what would be the main point in developing a computer chip that works much like the human brain? The ultimate goal is to create independent functioning machines that have the ability to take cues from their environment, change their courses, and complete their missions. At present, machines still need to be run through remote control because humans still have the most efficient decision making processes available. 

According to Professor Giacomo Indiveri from the Institute of Neuroinformatics (INI) the goal is to, “…emulate the properties of biological neurons and synapses directly on microchips” (University of Zurich).  In essence, you would have an independent machine that can adjust course, behavior, and actions based upon environmental information. This processing would be limited by the sensory systems attached to the system. 

There are some theoretical problems with the process. Unless the system can build new connections, behavioral models, and hardware independently it would not be able to mechanically/biological adapt to its environment. It would be limited by its design. Furthermore, it would be a rational machine that wouldn’t necessarily be able to use emotion to further those connections to create new forms of knowledge such as intuition. Data is only half the equation while emotion is the other. According to the French Mathematician Descartes emotion hampers decision making but others have argued it is truly part of and enhances the decision making process. 

In either event, it certainly will be interesting to figure out where all of this leads. Such machines might be of benefit in space, underwater, combat situations, and places where communication has been cut off. The development of miniaturization in manufacturing is likely to make these processing systems more efficient and capable of use in multiple arenas. We may soon have a machine that think as fast as we do but would be limited in its ability to intuitively “feel” its environment in the way humans can. The good news is that you could probably still confuse such a computer with questions that require an intuitive answer based in emotional judgement where the pieces don’t create the solution.