Goto

Collaborating Authors

 Country


A Connectionist Learning Approach to Analyzing Linguistic Stress

Neural Information Processing Systems

We use connectionist modeling to develop an analysis of stress systems in terms of ease of learnability. In traditional linguistic analyses, learnability arguments determine default parameter settings based on the feasibilty of logically deducing correct settings from an initial state. Our approach provides an empirical alternative tosuch arguments. Based on perceptron learning experiments using data from nineteen human languages, we develop a novel characterization of stress patterns in terms of six parameters. These provide both a partial description of the stress pattern itself and a prediction of its learnability, without invoking abstract theoretical constructs such as metrical feet. This work demonstrates that machine learningmethods can provide a fresh approach to understanding linguistic phenomena.



Extracting and Learning an Unknown Grammar with Recurrent Neural Networks

Neural Information Processing Systems

We show that similar methods are appropriate for learning unknown grammars from examples of their strings. TIle training algorithm is an incremental real-time, recurrent learning(RTRL) method that computes the complete gradient and updates the weights at the end ofeach string.


Competitive Anti-Hebbian Learning of Invariants

Neural Information Processing Systems

Although the detection of invariant structure in a given set of input patterns is vital to many recognition tasks, connectionist learning rules tend to focus on directions of high variance (principal components). The prediction paradigm is often used to reconcile this dichotomy; here we suggest a more direct approach to invariant learning based on an anti-Hebbian learning rule. An unsupervised tWO-layer network implementing this method in a competitive setting learns to extract coherent depth information from random-dot stereograms. 1 INTRODUCTION: LEARNING INVARIANT STRUCTURE Many connectionist learning algorithms share with principal component analysis (Jolliffe, 1986) the strategy of extracting the directions of highest variance from the input. A single Hebbian neuron, for instance, will come to encode the input's first principal component (Oja and Karhunen, 1985); various forms of lateral interaction can be used to force a layer of such nodes to differentiate and span the principal component subspace - cf. (Sanger, 1989; Kung, 1990; Leen, 1991), and others. The same type of representation also develops in the hidden layer of backpropagation autoassociator networks (Baldi and Hornik, 1989).


Operators and curried functions: Training and analysis of simple recurrent networks

Neural Information Processing Systems

We present a framework for programming tbe bidden unit representations of simple recurrent networks based on the use of hint units (additional targets at the output layer). We present two ways of analysing a network trained within this framework: Input patterns act as operators on the information encoded by the context units; symmetrically, patterns of activation over tbe context units act as curried functions of the input sequences. Simulations demonstrate that a network can learn to represent three different functions simultaneously and canonical discriminant analysis is used to investigate bow operators and curried functions are represented in the space of bidden unit activations.


Best-First Model Merging for Dynamic Learning and Recognition

Neural Information Processing Systems

Stephen M. Omohundro International Computer Science Institute 1947 CenteJ' Street, Suite 600 Berkeley, California 94704 Abstract "Best-first model merging" is a general technique for dynamically choosing the structure of a neural or related architecture while avoiding overfitting.It is applicable to both leaming and recognition tasks and often generalizes significantly better than fixed structures. We demonstrate theapproach applied to the tasks of choosing radial basis functions for function learning, choosing local affine models for curve and constraint surface modelling, and choosing the structure of a balltree or bumptree to maximize efficiency of access. 1 TOWARD MORE COGNITIVE LEARNING Standard backpropagation neural networks learn in a way which appears to be quite different fromhuman leaming. Viewed as a cognitive system, a standard network always maintains acomplete model of its domain. This model is mostly wrong initially, but gets gradually better and better as data appears. The net deals with all data in much the same way and has no representation for the strength of evidence behind a certain conclusion. The network architecture is usually chosen before any data is seen and the processing is much the same in the early phases of learning as in the late phases.


A Weighted Probabilistic Neural Network

Neural Information Processing Systems

The Probabilistic Neural Network (PNN) algorithm represents the likelihood functionof a given class as the sum of identical, isotropic Gaussians. In practice, PNN is often an excellent pattern classifier, outperforming other classifiers including backpropagation.


Networks for the Separation of Sources that are Superimposed and Delayed

Neural Information Processing Systems

We have created new networks to unmix signals which have been mixed either with time delays or via filtering. We first show that a subset of the Herault-Jutten learning rules fulfills a principle of minimum output power. We then apply this principle to extensions of the Herault-Jutten network which have delays in the feedback path. Our networks perform well on real speech and music signals that have been mixed using time delays or filtering.


Neural Computing with Small Weights

Neural Information Processing Systems

Kai-Yeung Siu Dept. of Electrical & Computer Engineering University of California, Irvine Irvine, CA 92717 Jehoshua Bruck IBM Research Division Almaden Research Center San Jose, CA 95120-6099 Abstract An important issue in neural computation is the dynamic range of weights in the neural networks. Many experimental results on learning indicate that the weights in the networks can grow prohibitively large with the size of the inputs. We show that there is an efficient way of simulating a network of LTEs with large weights by a network of LTEs with small weights. To prove these results, we use tools from harmonic analysis of Boolean functions. Our technique is quite general, it provides insights to some other problems.


Software for ANN training on a Ring Array Processor

Neural Information Processing Systems

Experimental research on Artificial Neural Network (ANN) algorithms requires either writing variations on the same program or making one monolithic program with many parameters and options. By using an object-oriented library, the size of these experimental programs is reduced while making them easier to read, write and modify. An efficient and flexible realization of this idea is Connectionist LayeredObject-oriented Network Simulator (CLONES).