Intelligent control and decision methods developed at the AI Center are based upon solid foundations provided by semantic logical models of the approximate-reasoning problem. These models are based on the notion of possible world. Informally, possible worlds correspond to the potential solutions of a system-analysis problem.

Gister supports the rapid development of evidential reasoning systems through an interactive, menu-driven, graphical interface, based upon Grasper-CL. The user interacts with the system in much the same way as with electronic spreadsheets, by simply selecting from menus to add evidential operations to an analysis, to modify data or operation parameters, or to change any portion of the uncertain knowledge base. In response, gister updates its analyses to reflect the new information. Gister supports a wide range of evidential operations, including fusion, source discounting, time projection, summarization, evidence interpretation, and sensitivity analysis. Gister has been applied to a wide range of problems, including multisensor interpretation, mission planning, medical diagnosis, intelligence analysis, underwater vehicle tracking, antiair threat identification, robot vehicle navigation, and management decision support.

Well, the lecture looks good, however, I have not understood the concepts of these neural networks and fuzzy logic on data analysis area. If we use the same data to model itself, then the question is what we are actually modeling - these simply turn out to be nothing but simply some form of advanced curve fitting tools. The most important feature would be if these tools can give us satisfactory modeling of some variables such as heat transfer coeffecient that cannot be measured easily from some other easily measurable variables, then only it makes sense. If it is the case of estimation and cross validation where the estimation depends on measured quantities, then modeling can be easily achieved such as using some dimensionless physical numbers and why we need the fuzzy logic or neural network in such cases, it is not clear yet.

Stuart Russell is a leading researcher in the field of artificial intelligence. He is a Professor of Computer Science at the University of California at Berkeley, Associate Editor of the Journal of the ACM, and author of "Artificial Intelligence: A Modern Approach" (Prentice Hall, 1995, 2003), the leading textbook in the field. His research interests include machine learning, limited rationality, real-time decision-making, intelligent agent architectures, autonomous vehicles, search, game-playing, reasoning under uncertainty, and commonsense knowledge representation. UBIQUITY: The original grand vision of artificial intelligence (AI) in the 1950s and '60s seemed to dissipate into many small, disparate projects. Should this fragmentation be written off as an inevitable Humpty-Dumpty problem or is it possible to bring the fragments back together into a single field? RUSSELL: I think we can put it back together in the sense of being able to join the pieces.

Will robots ever be able to learn the way humans do? After all, gathering data about one's environment is the easy part; the difficult part is being able to evaluate that information and adjust one's response to it. Answering the call to address this highly complicated and technical question is 31-year-old Ayanna Howard (pictured left), senior member of the Telerobotics Research and Applications Group at NASA's Jet Propulsion Laboratory (JPL) in Pasadena, California. She is developing a software program system that emulates human behavior for use in a Mars robot rover. The robot will search the surface of the Red Planet for evidence of water and life and will pave the way for human exploration.

You happen to know that Tim and Harry have recently had a terrible row that ended their friendship. Now someone tells you that she just saw Tim and Harry jogging together. The best explanation for this that you can think of is that they made up. You conclude that they are friends again. One morning you enter the kitchen to find a plate and cup on the table, with breadcrumbs and a pat of butter on it, and surrounded by a jar of jam, a pack of sugar, and an empty carton of milk. You conclude that one of your house-mates got up at night to make him- or herself a midnight snack and was too tired to clear the table. This, you think, best explains the scene you are facing. To be sure, it might be that someone burgled the house and took the time to have a bite while on the job, or a house-mate might have arranged the things on the table without having a midnight snack but just to make you believe that someone had a midnight snack. But these hypotheses strike you as providing much more contrived explanations of the data than the one you infer to. Walking along the beach, you see what looks like a picture of Winston Churchill in the sand. It could be that, as in the opening pages of Hilary Putnam's (1981), what you see is actually the trace of an ant crawling on the beach. The much simpler, and therefore (you think) much better, explanation is that someone intentionally drew a picture of Churchill in the sand. That, in any case, is what you come away believing. In these examples, the conclusions do not follow logically from the premises.

FuzzyCLIPS is a fuzzy logic extension of the CLIPS (C Language Integrated Production System) expert system shell from NASA. It was developed by the Integrated Reasoning Group of the Institute for Information Technology of the National Research Council of Canada and has been widely distributed for a number of years. It enhances CLIPS by providing a fuzzy reasoning capability that is fully integrated with CLIPS facts and inference engine allowing one to represent and manipulate fuzzy facts and rules. FuzzyCLIPS can deal with exact, fuzzy (or inexact), and combined reasoning, allowing fuzzy and normal terms to be freely mixed in the rules and facts of an expert system. The system uses two basic inexact concepts, fuzziness and uncertainty. It has provided a useful environment for developing fuzzy applications but it does require significant effort to update and maintain as new versions of CLIPS are released.

Sum-product networks have recently emerged as an attractive representation due to their dual view as a special type of deep neural network with clear semantics and a special type of probabilistic graphical model for which inference is always tractable. Those properties follow from some conditions (i.e., completeness and decomposability) that must be respected by the structure of the network. As a result, it is not easy to specify a valid sum-product network by hand and therefore structure learning techniques are typically used in practice. This paper describes the first online structure learning technique for continuous SPNs with Gaussian leaves. We also introduce an accompanying new parameter learning technique.

Influence diagrams provide a compact graphical representation of decision problems. Several algorithms for the quick computation of their associated expected utilities are available in the literature. However, often they rely on a full quantification of both probabilistic uncertainties and utility values. For problems where all random variables and decision spaces are finite and discrete, here we develop a symbolic way to calculate the expected utilities of influence diagrams that does not require a full numerical representation. Within this approach expected utilities correspond to families of polynomials. After characterizing their polynomial structure, we develop an efficient symbolic algorithm for the propagation of expected utilities through the diagram and provide an implementation of this algorithm using a computer algebra system. We then characterize many of the standard manipulations of influence diagrams as transformations of polynomials. We also generalize the decision analytic framework of these diagrams by defining asymmetries as operations over the expected utility polynomials.

Gaussian processes (GPs) have been proven to be powerful tools in various areas of machine learning. However, there are very few applications of GPs in the scenario of multi-view learning. In this paper, we present a new GP model for multi-view learning. Unlike existing methods, it combines multiple views by regularizing marginal likelihood with the consistency among the posterior distributions of latent functions from different views. Moreover, we give a general point selection scheme for multi-view learning and improve the proposed model by this criterion. Experimental results on multiple real world data sets have verified the effectiveness of the proposed model and witnessed the performance improvement through employing this novel point selection scheme.