Do you want your neural net algorithm to learn sequences? Do not limit yourselfto conventional gradient descent (or approximations thereof). Instead, use your sequence learning algorithm (any will do) to implement the following method for history compression. No matter what your final goalsare, train a network to predict its next input from the previous ones. Since only unpredictable inputs convey new information, ignore all predictable inputs but let all unexpected inputs (plus information about the time step at which they occurred) become inputs to a higher-level network of the same kind (working on a slower, self-adjusting time scale). Go on building a hierarchy of such networks.

Marques Pereira Dipartimento di Informatica Universita di Trento Via Inama 7, Trento, TN 38100 ITALY Abstract Learning a map from an input set to an output set is similar to the problem ofreconstructing hypersurfaces from sparse data (Poggio and Girosi, 1990). In this framework, we discuss the problem of automatically selecting "minimal"surface data. The objective is to be able to approximately reconstruct the surface from the selected sparse data. We show that this problem is equivalent to the one of compressing information by data removal andthe one oflearning how to teach. Our key step is to introduce a process that statistically selects the data according to the model. During the process of data selection (learning how to teach) our system (teacher) is capable of predicting the new surface, the approximated one provided by the selected data.

The localized linear discriminant network (LLDN) has been designed to address classification problems containing relatively closely spaced data from different classes (encounter zones [1], the accuracy problem [2]). Locally trained hyperplane segmentsare an effective way to define the decision boundaries for these regions [3]. The LLD uses a modified perceptron training algorithm for effective discovery of separating hyperplane/sigmoid units within narrow boundaries. The basic unit of the network is the discriminant receptive field (DRF) which combines the LLD function with Gaussians representing the dispersion of the local training data with respect to the hyperplane. The DRF implements a local distance measure [4],and obtains the benefits of networks oflocalized units [5]. A constructive algorithm for the two-class case is described which incorporates DRF's into the hidden layer to solve local discrimination problems. The output unit produces a smoothed, piecewise linear decision boundary. Preliminary results indicate the ability of the LLDN to efficiently achieve separation when boundaries are narrow and complex, in cases where both the "standard" multilayer perceptron (MLP) and k-nearest neighbor (KNN) yield high error rates on training data. 1 The LLD Training Algorithm and DRF Generation The LLD is defined by the hyperplane normal vector V and its "midpoint" M (a translated origin [1] near the center of gravity of the training data in feature space). Incremental corrections to V and M accrue for each training token feature vector Yj in the training set, as iIlustrated in figure 1 (exaggerated magnitudes).

Books in the Innovative Applications of Artificial for the documents they want.

Allen Newell was one of the founders and truly great scientists of AI. His contributions included foundational concepts and ground-breaking systems. His career was defined by the pursuit of a single, fundamental issue: the nature of the human mind. This article traces his pursuit from his early work on search and list processing in systems such as the LOGIC THEORIST and the GENERAL PROBLEM SOLVER; through his work on problem spaces, human problem solving, and production systems; through his final work on unified theories of cognition and SOAR.

I met Allen for the first time when I came for a two semester long visit to Carnegie Mellon University in 1968. This encounter was a distinct factor in my later decision to join the faculty at Carnegie Mellon University.

Allen Newell, one of the founders of AI and cognitive science, died on July 19th, 1992.

Models in the Mind: Theory Perspective, in Open Worlds: A Case Study in Design.

The Department of Computer Science at Louisiana State University (LSU) has been involved in robotics research since 1992 when the Robotics Research Laboratory (RRL) was established as a research and teaching program specializing in autonomous mobile robots (AMRS). Researchers at RRL are conducting high-quality research in amrs with the goal of identifying the computational problems and the types of knowledge that are fundamental to the design and implementation of autonomous mobile robotic systems. In this article, we overview the projects that are currently under way at LSU's RRL.

Alan Turing's decades-old question still influences artificial intelligence because of the simple test he proposed in his article in Mind. In this article, AI Magazine collects presentations about the first round of the classic Turing Test of machine intelligence, held November 8, 1991 at The Computer Museum, Boston. Robert Epstein, Director Emeritus, Cambridge Center for Behavioral Studies, and an adjunct professor of psychology, Boston University, University of Massachusetts (Amherst), and University of California (San Diego) summarizes some of the difficult issues during the planning of this first real-time competition, and describes the event. Presented in tandem with Dr. Epstein's article is the actual transcript of session that won the Loebner Prize Competition--Joseph Weintraub's computer program PC Therapist. In 1985 an old friend, Hugh Loebner, told me The intricacies of setting up a real Turing Test excitedly that the Turing Test should be made that would ultimately yield a legitimate into an annual contest. We were ambling winner were enormous. Small points were down a Manhattan street on our way to occasionally debated for months without dinner, as I recall. Hugh was always full of clear resolution. Turing, proposed a variation on a simple Four years later, while serving as the director parlor game as a means for identifying a of the Cambridge Center for Behavioral Studies, machine that can think: A human judge an advanced studies institute in Massachusetts, interacts with two computer terminals, one I established the Loebner Prize controlled by a computer and the other by a Competition, the first serious effort to locate person, but the judge doesn't know which is a machine that can pass the Turing Test. If, after a prolonged conversation at Hugh had come through with a pledge of each terminal, the judge can't tell the difference, $100,000 for the prize money, along with we'd have to say, asserted Turing, that some additional funds from his company, in some sense the computer is thinking. Crown Industries, to help with expenses. The Computers barely existed in Turing's day, but, quest for the thinking computer had begun. I'll then describe that After much debate, the Loebner Prize Committee first event, which took place on November 8, ultimately rejected Turing's simple 1991, at The Computer Museum in Boston two-terminal design in favor of one that is and offer a summary of some of the data generated more discriminating and less problematic. Finally, I'll speculate The two-terminal design is troublesome for about the future of the competition--now an several reasons, among them: The design presumes annual event, as Hugh envisioned--and that the hidden human--the human about its significance to the AI community.