To more precisely evaluate the implications of a neuronal model.

This paper provides a systematic analysis of the recurrent backpropagation (RBP) algorithm, introducing a number of new results. The main limitation of the RBP algorithm is that it assumes the convergence of the network to a stable fixed point in order to backpropagate the error signals. We show by experiment and eigenvalue analysis that this condition can be violated and that chaotic behavior can be avoided. Next we examine the advantages of RBP over the standard backpropagation algorithm. RBP is shown to build stable fixed points corresponding to the input patterns. This makes it an appropriate tool for content addressable memories, one-to-many function learning, and inverse problems.

We introduce a learning algorithm for multilayer neural networks composed of binary linear threshold elements. Whereas existing algorithms reduce the learning process to minimizing a cost function over the weights, our method treats the internal representations as the fundamental entities to be determined. Once a correct set of internal representations is arrived at, the weights are found by the local aild biologically plausible Perceptron Learning Rule (PLR). We tested our learning algorithm on four problems: adjacency, symmetry, parity and combined symmetry-parity.

ALVIS is a reinforcement-based connectionist architecture that learns associative maps in continuous multidimensional environments. The discovered locations of positive and negative reinforcements are recorded in "do be" and "don't be" subnetworks, respectively. The outputs of the subnetworks relevant to the current goal are combined and compared with the current location to produce an error vector. This vector is backpropagated through a motor-perceptual mapping network.

We propose a new neural network model and its learning algorithm. The proposed neural network consists of four layers - input, hidden, output and final output layers. The hidden and output layers are multiple. Using the proposed SICL(Spread Pattern Information and Cooperative Learning) algorithm, it is possible to learn analog data accurately and to obtain smooth outputs. Using this neural network, we have developed a speech production system consisting of a phonemic symbol production subsystem and a speech parameter production subsystem. We have succeeded in producing natural speech waves with high accuracy.

Reifsnider A number of learning models have recently been proposed which involve calculations of temporal differences (or derivatives in continuous-time models).

We have mathematically shown that cortical maps in the primary sensory cortices can be reproduced by using three hypotheses which have physiological basis and meaning. Here, our main focus is on ocular.dominance

Databases are at the heart of most real-world knowledge base systems. The management and effective use of these databases will be the limiting factors in our ability to build ever more complex AI systems. This article reports on a workshop that explored how databases and their associated technologies can best be used in the development of large AI applications.

AI Magazine Volume 10 Number 4 (1989) ( AAAI) generated some controversy. Relative to the discussion of the role of strong syllables in lexical segmentation, Gerry Altmann of CSTR reviewed some of the evidence based on computational studies of large The 1988 Workshop on Cognitive bone. Evidence from human studies computerized lexicons (20,000 Models of Speech Processing was suggested that the spurious word is words). This evidence suggested that held at Park Hotel Fiorelle, Sperlonga, activated, even though in principle it a stressed syllable conveys more Italy, on 16-20 May 1988. Twentyfive would be possible to prevent this activation information about the identity of the participants gathered in this by only accessing the lexicon at word in which it occurs than an small coastal village, where the the offset of some previously found unstressed syllable.

Commonsense reasoning about the physical world, as exemplified by "Iron sinks in water" or "If a ball is dropped it gains speed," will be indispensable in future programs. We argue that to make such predictions (namely, envisioning), programs should use abstract entities (such as the gravitational field), principles (such as the principle of superposition), and laws (such as the conservation of energy) of physics for representation and reasoning. These arguments are in accord with a recent study in physics instruction where expert problem solving is related to the construction of physical representations that contain fictitious, imagined entities such as forces and momenta (Larkin 1983). We give several examples showing the power of physical representations.