This papers describes and analyzes algorithms for learning linear threshold function (LTFs) in the presence of classiication noise and monotonic noise. When there is classiication noise, each randomly drawn example is mislabeled (i.e., diiers from the target LTF) with the same probability. For monotonic noise, the probability of mis-labeling an example monotonically decreases with the separatio...

An artificial neural network can be used as an intelligent controller to control non-linear, dynamic system through learning. It can easily accommodate non-linearities and time dependencies. Most common multi-layer feed-forward neural networks have the drawbacks of large number of neurons and hidden layers required to deal with complex problems and require large training time. To overcome these...

this paper presents a method for identification of linear system physical parameters (structural mass, damping and stiffness matrices) using the inverse solution of equation of motion in the frequency domain, by focus on the reducing the illconditioning effect. the method utilizes the measured responses from the forced vibration test of structure in order to identify the system properties and d...

We study the fundamental question of how query learn ing performs in imperfectly learnable problems where the student can only learn to approximate the teacher Considering as a prototypical sce nario a linear perceptron student learning a general nonlinear perceptron teacher we nd that queries for minimum entropy in student space i e maximum information gain lead to the same improvement in gene...

Presented here is a generalization of the implicit enumeration algorithm that can be applied when the objec-tive function is being maximized and can be rewritten as the difference of two non-decreasing functions. Also developed is a computational algorithm, named linear speedup, to use whatever explicit linear constraints are present to speedup the search for a solution. The method is easy to u...

Optimization is often the computational bottleneck in disciplines such as statistics, biology, physics, finance or economics. Many optimization problems can be directly cast in the wellstudied convex optimization framework. For non-convex problems, it is often possible to derive convex or spectral relaxations, i.e., derive approximations schemes using spectral or convex optimization tools. Conv...

We consider a sequence space model of statistical linear inverse problems where we need to estimate a function f from indirect noisy observations. Let a nite set of linear estimators be given. Our aim is to mimic the estimator in that has the smallest risk on the true f. Under general conditions, we show that this can be achieved by simple minimization of unbiased risk estimator, provided the s...

The generalized effective-medium theory of induced polarization (GEMTIP) is a newly developed relaxation model that incorporates the petro-physical and structural characteristics of polarizable rocks in the grain/porous scale to model their complex resistivity/conductivity spectra. The inversion of the GEMTIP relaxation model parameter from spectral-induced polarization data is a challenging is...