Industry
A Silicon Primitive for Competitive Learning
Hsu, David, Figueroa, Miguel, Diorio, Chris
Competitive learning is a technique for training classification and clustering networks. We have designed and fabricated an 11-transistor primitive, that we term an automaximizing bump circuit, that implements competitive learning dynamics. The circuit performs asimilarity computation, affords nonvolatile storage, and implements simultaneous local adaptation and computation. We show that our primitive is suitable for implementing competitive learning in VLSI, and demonstrate its effectiveness in a standard clustering task. 1 Introduction Competitive learning is a family of neural learning algorithms that has proved useful fortraining many classification and clustering networks [1]. In these networks, a neuron's synaptic weight vector typically represents a tight cluster of data points.
Sequentially Fitting ``Inclusive'' Trees for Inference in Noisy-OR Networks
Frey, Brendan J., Patrascu, Relu, Jaakkola, Tommi, Moran, Jodi
Forexample, in medical diagnosis, the presence of a symptom can be expressed as a noisy-OR of the diseases that may cause the symptom - on some occasions, a disease may fail to activate the symptom. Inference in richly-connected noisy-OR networks is intractable, butapproximate methods (e .g., variational techniques) are showing increasing promise as practical solutions. One problem withmost approximations is that they tend to concentrate on a relatively small number of modes in the true posterior, ignoring otherplausible configurations of the hidden variables. We introduce a new sequential variational method for bipartite noisy OR networks, that favors including all modes of the true posterior and models the posterior distribution as a tree. We compare this method with other approximations using an ensemble of networks with network statistics that are comparable to the QMR-DT medical diagnosticnetwork. 1 Inclusive variational approximations Approximate algorithms for probabilistic inference are gaining in popularity and are now even being incorporated into VLSI hardware (T.
Model Complexity, Goodness of Fit and Diminishing Returns
Cadez, Igor V., Smyth, Padhraic
Igor V. Cadez Information and Computer Science University of California Irvine, CA 92697-3425, U.S.A. PadhraicSmyth Information and Computer Science University of California Irvine, CA 92697-3425, U.S.A. Abstract We investigate a general characteristic of the tradeoff in learning problems between goodness-of-fit and model complexity. Specifically wecharacterize a general class of learning problems where the goodness-of-fit function can be shown to be convex within firstorder asa function of model complexity. This general property of "diminishing returns" is illustrated on a number of real data sets and learning problems, including finite mixture modeling and multivariate linear regression. 1 Introduction, Motivation, and Related Work Assume we have a data set D Such learning tasks can typically be characterized by the existence of a model and a loss function. A fitted model of complexity k is a function of the data points D and depends on a specific set of fitted parameters B. The loss function (goodnessof-fit) isa functional of the model and maps each specific model to a scalar used to evaluate the model, e.g., likelihood for density estimation or sum-of-squares for regression. Figure 1 illustrates a typical empirical curve for loss function versus complexity, for mixtures of Markov models fitted to a large data set of 900,000 sequences.
A Linear Programming Approach to Novelty Detection
Campbell, Colin, Bennett, Kristin P.
Novelty detection involves modeling the normal behaviour of a system henceenabling detection of any divergence from normality. It has potential applications in many areas such as detection of machine damageor highlighting abnormal features in medical data. One approach is to build a hypothesis estimating the support of the normal data i.e. constructing a function which is positive in the region where the data is located and negative elsewhere. Recently kernel methods have been proposed for estimating the support of a distribution and they have performed well in practice - training involves solution of a quadratic programming problem. In this paper wepropose a simpler kernel method for estimating the support based on linear programming. The method is easy to implement and can learn large datasets rapidly. We demonstrate the method on medical and fault detection datasets.
A New Model of Spatial Representation in Multimodal Brain Areas
Denรจve, Sophie, Duhamel, Jean-Renรฉ, Pouget, Alexandre
Most models of spatial representations in the cortex assume cells with limited receptive fields that are defined in a particular egocentric frameof reference. However, cells outside of primary sensory cortex are either gain modulated by postural input or partially shifting. We show that solving classical spatial tasks, like sensory prediction,multi-sensory integration, sensory-motor transformation andmotor control requires more complicated intermediate representations that are not invariant in one frame of reference. We present an iterative basis function map that performs these spatial tasks optimally with gain modulated and partially shifting units, and tests it against neurophysiological and neuropsychological data. In order to perform an action directed toward an object, it is necessary to have a representation of its spatial location.
Dendritic Compartmentalization Could Underlie Competition and Attentional Biasing of Simultaneous Visual Stimuli
Archie, Kevin A., Mel, Bartlett W.
Neurons in area V4 have relatively large receptive fields (RFs), so multiple visualfeatures are simultaneously "seen" by these cells. Recordings from single V4 neurons suggest that simultaneously presented stimuli compete to set the output firing rate, and that attention acts to isolate individual features by biasing the competition in favor of the attended object. We propose that both stimulus competition and attentional biasing arisefrom the spatial segregation of afferent synapses onto different regions of the excitable dendritic tree of V4 neurons. The pattern of feedforward, stimulus-driveninputs follows from a Hebbian rule: excitatory afferents with similar RFs tend to group together on the dendritic tree, avoiding randomly located inhibitory inputs with similar RFs. The same principle guides the formation of inputs that mediate attentional modulation.
Programmable Reinforcement Learning Agents
Andre, David, Russell, Stuart J.
We present an expressive agent design language for reinforcement learning thatallows the user to constrain the policies considered by the learning process.Thelanguage includes standard features such as parameterized subroutines,temporary interrupts, aborts, and memory variables, but also allows for unspecified choices in the agent program. For learning that which isn't specified, we present provably convergent learning algorithms. Wedemonstrate by example that agent programs written in the language are concise as well as modular. This facilitates state abstraction and the transferability of learned skills. 1 Introduction The field of reinforcement learning has recently adopted the idea that the application of prior knowledge may allow much faster learning and may indeed be essential if realworld environmentsare to be addressed. For learning behaviors, the most obvious form of prior knowledge provides a partial description of desired behaviors. Several languages for partial descriptions have been proposed, including Hierarchical Abstract Machines (HAMs) [8], semi-Markov options [12], and the MAXQ framework [4]. This paper describes extensions to the HAM language that substantially increase its expressive power,using constructs borrowed from programming languages. Obviously, increasing expressivenessmakes it easier for the user to supply whatever prior knowledge is available, and to do so more concisely.
Feature Selection for SVMs
Weston, Jason, Mukherjee, Sayan, Chapelle, Olivier, Pontil, Massimiliano, Poggio, Tomaso, Vapnik, Vladimir
We introduce a method of feature selection for Support Vector Machines. The method is based upon finding those features which minimize bounds on the leave-one-out error. This search can be efficiently performed via gradient descent. The resulting algorithms are shown to be superior to some standard feature selection algorithms on both toy data and real-life problems of face recognition, pedestrian detection and analyzing DNA micro array data. 1 Introduction In many supervised learning problems feature selection is important for a variety of reasons: generalizationperformance, running time requirements, and constraints and interpretational issuesimposed by the problem itself.
Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks
Hahnloser, Richard H. R., Seung, H. Sebastian
Ascribing computational principles to neural feedback circuits is an important problem in theoretical neuroscience. We study symmetric threshold-linearnetworks and derive stability results that go beyond the insights that can be gained from Lyapunov theory or energy functions. By applying linear analysis to subnetworks composed ofcoactive neurons, we determine the stability of potential steady states. We find that stability depends on two types of eigenmodes. Onetype determines global stability and the other type determines whether or not multistability is possible.
Discovering Hidden Variables: A Structure-Based Approach
Elidan, Gal, Lotner, Noam, Friedman, Nir, Koller, Daphne
A serious problem in learning probabilistic models is the presence of hidden variables.These variables are not observed, yet interact with several of the observed variables. As such, they induce seemingly complex dependencies amongthe latter. In recent years, much attention has been devoted to the development of algorithms for learning parameters, and in some cases structure, in the presence of hidden variables. In this paper, weaddress the related problem of detecting hidden variables that interact with the observed variables. This problem is of interest both for improving our understanding of the domain and as a preliminary step that guides the learning procedure towards promising models.