Based on an information theoretical approach, we investigate feature selection processes in saccadic object and scene analysis. Saccadic eye movements of human observers are recorded for a variety of natural and artificial test images. These experimental data are used for a statistical evaluation of the fixated image regions. Analysis of second-order statistics indicates that regions with higher spatial variance have a higher probability to be fixated, but no significant differences beyond these variance effects could be found at the level of power spectra. By contrast, an investigation with higher-order statistics, as reflected in the bispectral density, yielded clear structural differences between the image regions selected by saccadic eye movements as opposed to regions selected by a random process. These results indicate that nonredundant, intrinsically two-dimensional image features like curved lines and edges, occlusions, isolated spots, etc. play an important role in the saccadic selection process which must be integrated with top-down knowledge to fully predict object and scene analysis by human observers.

Computational mechanics, an approach to structural complexity, defines a process’s causal states and gives a procedure for finding them. We show that the causal-state representation—an E-machine—is the minimal one consistent with

Previous methods for soft shadows numerically integrate over many light directions at each receiver point, testing blocker visibility in each direction. We introduce a method for real-time soft shadows in dynamic scenes illuminated by large, low-frequency light sources where such integration is impractical. Our method operates on vectors representing low-frequency visibility of blockers in the spherical harmonic basis. Blocking geometry is modeled as a set of spheres; relatively few spheres capture the low-frequency blocking effect of complicated geometry. At each receiver point, we compute the product of visibility vectors for these blocker spheres as seen from the point. Instead of computing an expensive SH product per blocker as in previous work, we perform inexpensive vector sums to accumulate the log of blocker visibility. SH exponentiation then yields the product visibility vector over all blockers. We show how the SH exponentiation required can be approximated accurately and efficiently for low-order SH, accelerating previous CPUbased methods by a factor of 10 or more, depending on blocker complexity, and allowing real-time GPU implementation.

This thesis addresses a number of issues concerned with the restoration of one type of image sequence, namely archived black and white motion pictures. These are often a valuable historical record, but because of the physical nature of the film they can suffer from a variety of degradations which reduce their usefulness. The main visual defects are `dirt and sparkle' due to dust and dirt becoming attached to the film, or abrasion removing the emulsion, and `line scratches' due to the film running against foreign bodies in the camera or projector. For an image

Emnet for n rv rende licentiatafhandling er design af neurale netv rks ltre. Filtre baseret pa neurale netv rk kan ses som udvidelser af det klassiske line re adaptive l-ter rettet mod modellering af uline re sammenh nge. Hovedv gten l gges pa en neural netv rks implementering af den ikke-rekursive, uline re adaptive model med additiv st j. Formalet er at klarl gge en r kke faser forbundet med design af neural netv rks arkitekturer med henblik pa at udf re forskellige \black-box " modellerings opgaver sa som: System identi kation, invers modellering og pr diktion af tidsserier. De v senligste bidrag omfatter: Formulering af en neural netv rks baseret kanonisk lter repr sentation, der danner baggrund for udvikling af et arkitektur klassi kationssystem. I hovedsagen drejer det sig om en skelnen mellem globale og lokale modeller. Dette leder til at en r kke kendte neurale netv rks arkitekturer kan klassi ceres, og yderligere abnes der mulighed for udvikling af helt nye strukturer. I denne sammenh ng ndes en gennemgang af en r kke velkendte arkitekturer. I s rdeleshed l gges der v gt pa behandlingen af multi-lags perceptron neural netv rket.

. Consider a multilayer perceptron (MLP) with d inputs, a single hidden sigmoidal layer and a linear output. By adding an additional d inputs to the network with values set to the square of the first d inputs, properties reminiscent of higher-order neural networks and radial basis function networks (RBFN) are added to the architecture with little added expense in terms of weight requirements. Of particular interest, this architecture has the ability to form localized features in a d-dimensional space with a single hidden node but can also span large volumes of the input space; thus, the architecture has the localized properties of an RBFN but does not suffer as badly from the curse of dimensionality. I refer to a network of this type as a SQuare Unit Augmented, Radially Extended, MultiLayer Perceptron (SQUARE-MLP or SMLP). 1 Introduction and Motivation When faced with a new and challenging problem, the most crucial decision that a neural network researcher must make is in...

In this paper we present a generalization of popular linear model reduction methods, such as Lanczos- and Arnoldi-based algorithms based on rational approximation, to systems whose response to interesting external inputs can be described by a few terms in a functional series expansion such as a Volterra series. The approach allows automatic generation of macromodels that include frequency-dependent nonlinear effects.

Experimental data show that biological synapses behave quite differently from the symbolic synapses in all common artificial neural network models. Biological synapses are

We introduce a mechanism for constructing and training a hybrid architecture of projection based units and radial basis functions. In particular, we introduce an optimization scheme which includes several steps and assures a convergence to a useful solution. During network architecture construction and training, it is determined whether a unit should be removed or replaced. The resulting architecture has often smaller number of units compared with competing architectures. A specific overfitting resulting from shrinkage of the RBF radii is addressed by introducing a penalty on small radii. Classification and regression results are demonstrated on various benchmark data sets and compared with several variants of RBF networks [?, ?]. A striking performance improvement is achieved on the vowel data set [?]. Keywords: Projection units, RBF Units, Hybrid Network Architecture, SMLP, Clustering, Regularization. 1

Truncated Volterra expansions model nonlinear systems encountered with satellite communications, magnetic recording channels, and physiological processes. A general approach for blind deconvolution of single-input multiple-output Volterra finite impulse response (FIR) systems is presented. It is shown that such nonlinear systems can be blindly equalized using only linear FIR filters. The approach requires that the Volterra kernels satisfy a certain coprimeness condition and that the input possesses a minimal persistence-of-excitation order. No other special conditions are imposed on the kernel transfer functions or on the input signal, which may be deterministic or random with unknown statistics. The proposed algorithms are corroborated with simulation examples.