Industry
A New Technique Enables Dynamic Replanning and Rescheduling of Aeromedical Evacuation
Kott, Alexander, Saks, Victor, Mercer, Albert
We describe an application of a dynamic replanning technique in a highly dynamic and complex domain: the military aeromedical evacuation of patients to medical treatment facilities. U.S. Transportation Command (USTRANSCOM) is the U.S. Department of Defense (DoD) agency responsible for evacuating patients during wartime and peace. Doctrinally, patients requiring extended treatment must be evacuated by air to a suitable medical treatment facility. The Persian Gulf War was the first significant armed conflict in which this concept was put to a serious test. The results were far from satisfactory -- about 60 percent of the patients ended up at the wrong destinations. In early 1993, the DoD tasked USTRANSCOM to consolidate the command and control of medical regulation and aeromedical evacuation operations. The ensuing analysis led to TRAC2ES (TRANSCOM regulating and command and control evacuation system), a decision support system for planning and scheduling medical evacuation operations. Probably the most challenging aspect of the problem has to do with the dynamics of a domain in which requirements and constraints continuously change over time. Continuous dynamic replanning is a key capability of TRAC2ES. This article describes the application and the AI approach we took in providing this capability.
TDLeaf(lambda): Combining Temporal Difference Learning with Game-Tree Search
Baxter, Jonathan, Tridgell, Andrew, Weaver, Lex
In this paper we present TDLeaf(lambda), a variation on the TD(lambda) algorithm that enables it to be used in conjunction with minimax search. We present some experiments in both chess and backgammon which demonstrate its utility and provide comparisons with TD(lambda) and another less radical variant, TD-directed(lambda). In particular, our chess program, ``KnightCap,'' used TDLeaf(lambda) to learn its evaluation function while playing on the Free Internet Chess Server (FICS, fics.onenet.net). It improved from a 1650 rating to a 2100 rating in just 308 games. We discuss some of the reasons for this success and the relationship between our results and Tesauro's results in backgammon.
Analog VLSI Model of Intersegmental Coordination with Nearest-Neighbor Coupling
Patel, Girish N., Holleman, Jeremy H., DeWeerth, Stephen P.
We have a developed an analog VLSI system that models the coordination of neurobiological segmental oscillators. We have implemented and tested a system that consists of a chain of eleven pattern generating circuits that are synaptically coupled to their nearest neighbors. Each pattern generating circuit is implemented with two silicon Morris-Lecar neurons that are connected in a reciprocally inhibitory network. We discuss the mechanisms of oscillations in the two-cell network and explore system behavior based on isotropic and anisotropic coupling, and frequency gradients along the chain of oscillators.
A Hippocampal Model of Recognition Memory
O', Reilly, Randall C., Norman, Kenneth A., McClelland, James L.
A rich body of data exists showing that recollection of specific information makes an important contribution to recognition memory, which is distinct from the contribution of familiarity, and is not adequately captured by existing unitary memory models. Furthennore, neuropsychological evidence indicates that recollection is sub served by the hippocampus. We present a model, based largely on known features of hippocampal anatomy and physiology, that accounts for the following key characteristics of recollection: 1) false recollection is rare (i.e., participants rarely claim to recollect having studied nonstudied items), and 2) increasing interference leads to less recollection but apparently does not compromise the quality of recollection (i.e., the extent to which recollected infonnation veridically reflects events that occurred at study).
Hybrid Reinforcement Learning and Its Application to Biped Robot Control
Yamada, Satoshi, Watanabe, Akira, Nakashima, Michio
Advanced Technology R&D Center Mitsubishi Electric Corporation Amagasaki, Hyogo 661-0001, Japan Abstract A learning system composed of linear control modules, reinforcement learningmodules and selection modules (a hybrid reinforcement learning system) is proposed for the fast learning of real-world control problems. The selection modules choose one appropriate control module dependent on the state. It learned the control on a sloped floor more quickly than the usual reinforcement learningbecause it did not need to learn the control on a flat floor, where the linear control module can control the robot. When it was trained by a 2-step learning (during the first learning step, the selection module was trained by a training procedure controlled onlyby the linear controller), it learned the control more quickly. The average number of trials (about 50) is so small that the learning system is applicable to real robot control. 1 Introduction Reinforcement learning has the ability to solve general control problems because it learns behavior through trial-and-error interactions with a dynamic environment.
Neural Basis of Object-Centered Representations
Denรจve, Sophie, Pouget, Alexandre
We present a neural model that can perform eye movements to a particular side of an object regardless of the position and orientation ofthe object in space, a generalization of a task which has been recently used by Olson and Gettner [4] to investigate the neural structureof object-centered representations. Our model uses an intermediate representation in which units have oculocentric receptive fields-just like collicular neurons-whose gain is modulated by the side of the object to which the movement is directed, as well as the orientation of the object. We show that these gain modulations are consistent with Olson and Gettner's single cell recordings in the supplementary eye field. This demonstrates that it is possible to perform an object-centered task without a representation involving anobject-centered map, viz., without neurons whose receptive fields are defined in object-centered coordinates. We also show that the same approach can account for object-centered neglect, a situation inwhich patients with a right parietal lesion neglect the left side of objects regardless of the orientation of the objects. Several authors have argued that tasks such as object recognition [3] and manipulation [4]are easier to perform if the object is represented in object-centered coordinates, arepresentation in which the subparts of the object are encoded with respect to a frame of reference centered on the object. Compelling evidence for the existence of such representations in the cortex comes from experiments on hemineglect-a neurological syndrome resulting from unilateral lesions of the parietal cortex such that a right lesion, for example, leads patients to ignore stimuli located on the left side of their egocentric space. Recently, Driver et al. (1994) showed that the deficit can also be object-centered.
Correlates of Attention in a Model of Dynamic Visual Recognition
Given a set ofobjects in the visual field, how does the the visual system learn to attend to a particular object of interest while ignoring the rest? How are occlusions and background clutter so effortlessly discounted for when recognizing afamiliar object? In this paper, we attempt to answer these questions in the context of a Kalman filter-based model of visual recognition that has previously proved useful in explaining certain neurophysiological phenomena suchas endstopping and related extra-classical receptive field effects in the visual cortex. By using results from the field ofrobust statistics, we describe an extension of the Kalman filter model that can handle multiple objects in the visual field. The resulting robust Kalman filter model demonstrates howcertain forms of attention can be viewed as an emergent property of the interaction between top-down expectations and bottom-up signals.
Experiences with Bayesian Learning in a Real World Application
Sykacek, Peter, Dorffner, Georg, Rappelsberger, Peter, Zeitlhofer, Josef
This paper reports about an application of Bayes' inferred neural network classifiers in the field of automatic sleep staging. The reason for using Bayesian learning for this task is twofold. First, Bayesian inference is known to embody regularization automatically. Second, a side effect of Bayesian learning leads to larger variance of network outputs in regions without training data. This results in well known moderation effects, which can be used to detect outliers. In a 5 fold cross-validation experiment the full Bayesian solution found with R. Neals hybrid Monte Carlo algorithm, was not better than a single maximum a-posteriori (MAP) solution found with D.J. MacKay's evidence approximation. In a second experiment we studied the properties of both solutions in rejecting classification of movement artefacts.
An Analog VLSI Model of the Fly Elementary Motion Detector
Harrison, Reid R., Koch, Christof
Flies are capable of rapidly detecting and integrating visual motion information in behaviorly-relevant ways. The first stage of visual motion processing in flies is a retinotopic array of functional units known as elementary motion detectors (EMDs). Several decades ago, Reichardt and colleagues developed a correlation-based model of motion detection that described the behavior of these neural circuits. We have implemented a variant of this model in a 2.0-JLm analog CMOS VLSI process. The result is a low-power, continuous-time analog circuit with integrated photoreceptors that responds to motion in real time. The responses of the circuit to drifting sinusoidal gratings qualitatively resemble the temporal frequency response, spatial frequency response, and direction selectivity of motion-sensitive neurons observed in insects. In addition to its possible engineering applications, the circuit could potentially be used as a building block for constructing hardware models of higher-level insect motion integration.