Geoffrey Towell Siemens Corporate Research 755 College Road East Princeton, NJ 08540 Abstract Many classification problems have the property that the only costly part of obtaining examples is the class label. This paper suggests a simple method for using distribution information contained in unlabeled examples to augment labeled examples in a supervised training framework. Empirical tests show that the technique described inthis paper can significantly improve the accuracy of a supervised learner when the learner is well below its asymptotic accuracy level. 1 INTRODUCTION Supervised learning problems often have the following property: unlabeled examples have little or no cost while class labels have a high cost. For example, it is trivial to record hours of heartbeats from hundreds of patients. However, it is expensive to hire cardiologists to label each of the recorded beats.

AndersKrogh'" NORDITA, Blegdamsvej 17 2100 Copenhagen, Denmark kroghGsanger.ac.uk Abstract We study the characteristics of learning with ensembles. Solving exactly the simple model of an ensemble of linear students, we find surprisingly rich behaviour. For learning in large ensembles, it is advantageous to use under-regularized students, which actually over-fitthe training data. Globally optimal performance can be obtained by choosing the training set sizes of the students appropriately. Forsmaller ensembles, optimization of the ensemble weights can yield significant improvements in ensemble generalization performance,in particular if the individual students are subject to noise in the training process. Choosing students with a wide range of regularization parameters makes this improvement robust against changes in the unknown level of noise in the training data. 1 INTRODUCTION An ensemble is a collection of a (finite) number of neural networks or other types of predictors that are trained for the same task.

An extended version of the dual constraint model of motor endplate morphogenesisis presented that includes activity dependent and independent competition. It is supported by a wide range of recent neurophysiological evidence that indicates a strong relationship betweensynaptic efficacy and survival. The computational model is justified at the molecular level and its predictions match the developmental and regenerative behaviour of real synapses.

We describe the reinforcement learning problem, motivate algorithms whichseek an approximation to the Q function, and present new convergence results for two such algorithms. 1 INTRODUCTION AND BACKGROUND Imagine an agent acting in some environment. At time t, the environment is in some state Xt chosen from a finite set of states. The agent perceives Xt, and is allowed to choose an action at from some finite set of actions. Meanwhile, the agent experiences a real-valued cost Ct, chosen from a distribution which also depends only on Xt and at and which has finite mean and variance. Such an environment is called a Markov decision process, or MDP.

"Topographic" mappings occur frequently in the brain. A popular approachto understanding the structure of such mappings is to map points representing input features in a space of a few dimensions to points in a 2 dimensional space using some selforganizing algorithm.We argue that a more general approach may be useful, where similarities between features are not constrained tobe geometric distances, and the objective function for topographic matching is chosen explicitly rather than being specified implicitlyby the self-organizing algorithm. We investigate analytically an example of this more general approach applied to the structure of interdigitated mappings, such as the pattern of ocular dominance columns in primary visual cortex. 1 INTRODUCTION A prevalent feature of mappings in the brain is that they are often "topographic". In the most straightforward case this simply means that neighbouring points on a two-dimensional sheet (e.g. the retina) are mapped to neighbouring points in a more central two-dimensional structure (e.g. the optic tectum). However a more complex case, still often referred to as topographic, is the mapping from an abstract space of features (e.g.

The existence of significant delays in sensorimotor feedback pathways has led several researchers to suggest that the cerebellum might function as a forward model of the motor plant in order to predict the sensory consequences of motor commands before actual feedback is available; e.g., (Ito, 1984; Keeler, 1990; Miall et ai., 1993). While we agree that there are many potential roles for forward models in motor control systems, as discussed, e.g., in (Wolpert et al., 1995), we present a hypothesis about how the cerebellum could participate in regulating movement in the presence of significant feedbackdelays without resorting to a forward model. We show how a very simplified version of the adjustable pattern generator (APG) model being developed by Houk and colleagues (Berthier et al., 1993; Houk et al., 1995) can learn to control endpointpositioning of a nonlinear spring-mass system with significant delays in both afferent and efferent pathways. Although much simpler than a multilink dynamic arm, control of this spring-mass system involves some of the challenges critical in the control of a more realistic motor system and serves to illustrate the principles we propose. Preliminary results appear in (Buckingham et al., 1995).

Reinforcement learning has become one of the most actively studied learning frameworks in the area of intelligent autonomous agents. This article describes the results of a three-day meeting of leading researchers in this area that was sponsored by the National Science Foundation. Because reinforcement learning is an interdisciplinary topic, the workshop brought together researchers from a variety of fields, including machine learning, neural networks, AI, robotics, and operations research. The goals of the meeting were to (1) understand limitations of current reinforcement-learning systems and define promising directions for further research; (2) clarify the relationships between reinforcement learning and existing work in engineering fields, such as operations research; and (3) identify potential industrial applications of reinforcement learning.

Inherent batch-to-batch variability, aging, and contamination are major factors contributing to variability in oil-field cement-slurry performance. Such variability imposes a heavy burden on performance testing and is often a major factor in operational failure. Our approach involves predicting cement compositions, particle-size distributions, and thickening-time curves from the diffuse reflectance infrared Fourier transform spectrum of neat cement powders. Our research shows that many key cement properties are captured within the Fourier transform infrared spectra of cement powders and can be predicted from these spectra using suitable neural network techniques.

As part of a collaboration with the White House Office of Media Affairs, members of the Artificial Intelligence Laboratory at the Massachusetts Institute of Technology designed a system, called COMLINK, that distributes a daily stream of documents released by the Office of Media Affairs. Approximately 4,000 direct subscribers receive information from this service, but more than 100,000 people receive the information through redistribution channels. The information is distributed through e-mail and the World Wide Web. These invalid subscriptions cause a backwash of hundreds of bounced-mail messages each day that must be processed by the operators of the COMLINK system.

An important problem faced by auditors is gauging how much reliance can be placed on the accounting systems that process millions of transactions to produce the numbers summarized in a company's financial statements. In a complex accounting system, it can be an extremely difficult task for the auditor to anticipate the possible errors that can occur and evaluate the effectiveness of the controls at detecting them. An accurate analysis must take into account the unique features of each company's business processes. An auditor uses COMET to create a hierarchical flowchart model that describes the intended processing of business transactions by an accounting system and the operation of its controls.