Goto

Collaborating Authors

 Industry


A Network of Localized Linear Discriminants

Neural Information Processing Systems

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).


Forward Dynamics Modeling of Speech Motor Control Using Physiological Data

Neural Information Processing Systems

We propose a paradigm for modeling speech production based on neural networks. We focus on characteristics of the musculoskeletal system. Using real physiological data - articulator movements and EMG from muscle activitya neuralnetwork learns the forward dynamics relating motor commands to muscles and the ensuing articulator behavior. After learning, simulated perturbations, were used to asses properties of the acquired model, such as natural frequency, damping, and interarticulator couplings. Finally, a cascade neural network is used to generate continuous motor commands from a sequence of discrete articulatory targets.


A Neural Network for Motion Detection of Drift-Balanced Stimuli

Neural Information Processing Systems

This paper briefly describes an artificial neural network for preattentive visual processing. The network is capable of determiuing image motioll in a type of stimulus which defeats most popular methods of motion detect.ion


Locomotion in a Lower Vertebrate: Studies of the Cellular Basis of Rhythmogenesis and Oscillator Coupling

Neural Information Processing Systems

To test whether the known connectivies of neurons in the lamprey spinal cord are sufficient to account for locomotor rhythmogenesis, a CCconnectionist" neuralnetwork simulation was done using identical cells connected according toexperimentally established patterns. It was demonstrated that the network oscillates in a stable manner with the same phase relationships amongthe neurons as observed in the lamprey. The model was then used to explore coupling between identical?scillators. It was concluded that the neurons can have a dual role as rhythm generators and as coordinators betweenoscillators to produce the phase relations observed among segmental oscillators during swimming.


Single Neuron Model: Response to Weak Modulation in the Presence of Noise

Neural Information Processing Systems

THE MODEL; STOCHASTIC RESONANCE The reduced neuron model consists of a single Hopfield-type computational element, which may be modeled as a R-C circuit with nonlinear feedback provided by an operational amplifier having a sigmoid transfer function.


Information Processing to Create Eye Movements

Neural Information Processing Systems

Because eye muscles never cocontract and do not deal with external loads, one can write an equation that relates motoneuron firing rate to eye position and velocity - a very uncommon situation in the CNS. The semicircular canals transduce head velocity in a linear manner by using a high background discharge rate, imparting linearity to the premotor circuits that generate eye movements. This has allowed deducing some of the signal processing involved, including a neural network that integrates. These ideas are often summarized by block diagrams. Unfortunately, they are of little value in describing the behavior of single neurons - a fmding supported by neural network models.


A Cortico-Cerebellar Model that Learns to Generate Distributed Motor Commands to Control a Kinematic Arm

Neural Information Processing Systems

A neurophysiologically-based model is presented that controls a simulated kinematic arm during goal-directed reaches. The network generates a quasi-feedforward motor command that is learned using training signals generated by corrective movements. For each target, the network selects and sets the output of a subset of pattern generators. During the movement, feedbackfrom proprioceptors turns off the pattern generators. The task facing individual pattern generators is to recognize when the arm reaches the target and to turn off. A distributed representation of the motor commandthat resembles population vectors seen in vivo was produced naturally by these simulations.



AI Research and Applications in Digital's Service Organization

AI Magazine

The Digital Services Research Group and its predecessor groups and offshoots in Digital Equipment Corporation have been mobilizing leading-edge AI research to bear on real-life problems that face the corporation and its customers. The general strategy of the group is to explore emerging techniques relevant to service and support needs through developing rapid prototypes, deploying these prototypes, and incorporating feedback from users. With over 32 major projects undertaken during the past decade, we have worked on broad spectrum of problems and explored a variety of advanced AI techniques. This article describes the current AI activities in five areas: (1) enterprise advisory systems, (2) natural language processing and textual information retrieval, (3) largescale knowledge base management and access, (4) software configuration management, and (5) intrusion detection.


The AI Program at the National Aeronautics and Space Administration: Lessons Learned During the First Seven Years

AI Magazine

This article is a slightly modified version of an invited address that was given at the Eighth IEEE Conference on Artificial Intelligence for Applications in Monterey, California, on 2 March 1992. It describes the lessons learned in developing and implementing the Artificial Intelligence Research and Development Program at the National Aeronautics and Space Administration (NASA). These stages are similar to the "ages of artificial intelligence" that Pat Winston described a year before the NASA program was initiated. The final section of the article attempts to generalize some of the lessons learned during the first seven years of the NASA AI program into AI program management heuristics.