Learning structure in temporally-extended sequences is a difficult computational problembecause only a fraction of the relevant information is available at any instant. Although variants of back propagation can in principle be used to find structure in sequences, in practice they are not sufficiently powerful to discover arbitrary contingencies, especially those spanning long temporal intervals or involving high order statistics. For example, in designing a connectionist network for music composition, we have encountered the problem that the net is able to learn musical structure thatoccurs locally in time-e.g., relations among notes within a musical phrase-butnot structure that occurs over longer time periods--e.g., relations among phrases. To address this problem, we require a means of constructing a reduced deacription of the sequence that makes global aspects more explicit or more readily detectable. I propose to achieve this using hidden units that operate with different time constants.

Standard pattern recognition systems usually involve a segmentation step prior to the recognition step. For example, it is very common in character recognition to segment characters in a pre-processing step then normalize the individual characters and pass them to a recognition engine such as a neural network, as in the work of LeCun et al. 1988, Martin and Pittman (1988). This separation between segmentation and recognition becomes unreliable if the characters are touching each other, touching bounding boxes, broken, or noisy. Other applications such as scene analysis or continuous speech recognition pose similar and more severe segmentation problems. The difficulties encountered in these applications present an apparent dilemma: one cannot recognize the patterns 496 *keeler@mcc.comReprint

Recently synchronization phenomena in neural networks have attracted considerable attention. Gray et al. (1989, 1990) as well as Eckhorn et al. (1988) provided electrophysiological evidence that neurons in the visual cortex of cats discharge in a semi-synchronous, oscillatory manner in the 40 Hz range and that the firing activity of neurons up to 10 mm away is phase-locked with a mean phase-shift of less than 3 msec. It has been proposed that this phase synchronization can solve the binding problem for figure-ground segregation (von der Malsburg and Schneider, 1986) and underly visual attention and awareness (Crick and Koch, 1990). A number of theoretical explanations based on coupled (relaxation) oscillator mod-117 118 Schuster and Koch els have been proposed for burst synchronization (Sompolinsky et al., 1990). The crucial issue of phase synchronization has also recently been addressed by Bush and Douglas (1991), who simulated the dynamics of a network consisting of bursty, layer V pyramidal cells coupled to a common pool of basket cells inhibiting all pyramidal cells.

It has been observed in numerical simulations that a weight decay can improve generalizationin a feed-forward neural network.

Existing metrics for the learning performance of feed-forward neural networks do not provide a satisfactory basis for comparison because the choice of the training epoch limit can determine the results of the comparison. I propose new metrics which have the desirable property of being independent of the training epoch limit. The efficiency measures the yield of correct networks in proportion to the training effort expended. The optimal epoch limit provides the greatest efficiency. The learning performance is modelled statistically, and asymptotic performance is estimated. Implementation details may be found in (Harney, 1992). 1 Introduction The empirical comparison of neural network training algorithms is of great value in the development of improved techniques and in algorithm selection for problem solving. In view of the great sensitivity of learning times to the random starting weights (Kolen and Pollack, 1990), individual trial times such as reported in (Rumelhart, et al., 1986) are almost useless as measures of learning performance.

Despite the fact that complex visual scenes contain multiple, overlapping objects, people perform object recognition with ease and accuracy. One operation that facilitates recognition is an early segmentation process in which features of objects are grouped and labeled according to which object theybelong. Current computational systems that perform this operation arebased on predefined grouping heuristics.

I present a modular network architecture and a learning algorithm based on incremental dynamic programming that allows a single learning agent to learn to solve multiple Markovian decision tasks (MDTs) with significant transferof learning across the tasks. I consider a class of MDTs, called composite tasks, formed by temporally concatenating a number of simpler, elemental MDTs. The architecture is trained on a set of composite andelemental MDTs. The temporal structure of a composite task is assumed to be unknown and the architecture learns to produce a temporal decomposition.It is shown that under certain conditions the solution of a composite MDT can be constructed by computationally inexpensive modifications of the solutions of its constituent elemental MDTs. 1 INTRODUCTION Most applications of domain independent learning algorithms have focussed on learning single tasks. Building more sophisticated learning agents that operate in complex environments will require handling multiple tasks/goals (Singh, 1992). Research efforton the scaling problem has concentrated on discovering faster learning algorithms, and while that will certainly help, techniques that allow transfer of learning across tasks will be indispensable for building autonomous learning agents that have to learn to solve multiple tasks. In this paper I consider a learning agent that interacts with an external, finite-state, discrete-time, stochastic dynamical environment andfaces multiple sequences of Markovian decision tasks (MDTs).

Here during the production event a very low infonnational input ("Madonna," and "Matisse") is used

Gold Center for Neural Science, Brown University Providence, RI 02912, USA Shimon Edelman Dept. of Applied Mathematics and Computer Science, Weizmann Institute of Science, Rehovot 76100, Israel Abstract Intrator (1990) proposed a feature extraction method that is related to recent statistical theory (Huber, 1985; Friedman, 1987), and is based on a biologically motivated model of neuronal plasticity (Bienenstock et al., 1982). This method has been recently applied to feature extraction in the context of recognizing 3D objects from single 2D views (Intrator and Gold, 1991). Here we describe experiments designed to analyze the nature of the extracted features, and their relevance to the theory and psychophysics of object recognition. 1 Introduction Results of recent computational studies of visual recognition (e.g., Poggio and Edelman, 1990)indicate that the problem of recognition of 3D objects can be effectively reformulated in terms of standard pattern classification theory. According to this approach, an object is represented by a few of its 2D views, encoded as clusters in multidimentional space. Recognition of a novel view is then carried out by interpo-460 3D Object Recognition Using Unsupervised Feature Extraction 461 lating among the stored views in the representation space.

Automated monitoring of vigilance in attention intensive tasks such as air traffic control or sonar operation is highly desirable. As the operator monitorsthe instrument, the instrument would monitor the operator, insuring against lapses. We have taken a first step toward this goal by using feedforwardneural networks trained with backpropagation to interpret event related potentials (ERPs) and electroencephalogram (EEG) associated withperiods of high and low vigilance. The accuracy of our system on an ERP data set averaged over 28 minutes was 96%, better than the 83% accuracy obtained using linear discriminant analysis. Practical vigilance monitoring will require prediction over shorter time periods. We were able to average the ERP over as little as 2 minutes and still get 90% correct prediction of a vigilance measure. Additionally, we achieved similarly good performance using segments of EEG power spectrum as short as 56 sec.