Digital Commons Network^™

Grundlagenreflexionen Zur Thematik Anthropomorpher Schnittstellen, Rudolf Kaehr

Rudolf Kaehr

Report for the EMBASSI Project

Fuzzy Neural Network Models For Supervised Classification: Multispectral Image Analysis, Arun D. Kulkarni, Kamlesh Lulla

Arun Kulkarni

No abstract provided.

Computational Complexity For Continuous Time Dynamics, Hava Siegelmann, Asa Ben-Hur, Shmuel Fishman

Hava Siegelmann

Dissipative flows model a large variety of physical systems. In this Letter the evolution of such systems is interpreted as a process of computation; the attractor of the dynamics represents the output. A framework for an algorithmic analysis of dissipative flows is presented, enabling the comparison of the performance of discrete and continuous time analog computation models. A simple algorithm for finding the maximum of n numbers is analyzed, and shown to be highly efficient. The notion of tractable (polynomial) computation in the Turing model is conjectured to correspond to computation with tractable (analytically solvable) dynamical systems having polynomial complexity.

Probabilistic Crowding: Deterministic Crowding With Probabilistic Replacement, Ole J. Mengshoel, David E. Goldberg

Ole J Mengshoel

This paper presents a novel niching algorithm, probabilistic crowding. Like its predecessor deterministic crowding, probabilistic crowding is fast, simple, and requires no parameters beyond that of the classical GA. In probabilistic crowding, subpopulations are maintained reliably, and we analyze and predict how this maintenance takes place.

This paper also identifies probabilistic crowding as a member of a family of algorithms, which we call integrated tournament algorithms. Integrated tournament algorithms also include deterministic crowding, restricted tournament selection, elitist recombination, parallel recombinative simulated annealing, the Metropolis algorithm, and simulated annealing.

Discontinuities In Recurrent Neural Networks, R. Gavaldà, Hava Siegelmann

Hava Siegelmann

This article studies the computational power of various discontinuous real computational models that are based on the classical analog recurrent neural network (ARNN). This ARNN consists of finite number of neurons; each neuron computes a polynomial net function and a sigmoid-like continuous activation function. We introduce arithmetic networks as ARNN augmented with a few simple discontinuous (e.g., threshold or zero test) neurons. We argue that even with weights restricted to polynomial time computable reals, arithmetic networks are able to compute arbitrarily complex recursive functions. We identify many types of neural networks that are at least as powerful as arithmetic nets, …

Modelowanie Stężenia Ozonu W Niskiej Troposferze Na Przykładzie Nowego Sącza, Marek Bogacki, Marek Mazur, Robert Oleniacz

Robert Oleniacz

The paper presents the results of research related to the modeling of physicochemical phenomena occurring in the ground layer of the atmosphere in terms of ozone formation. For this purpose, the box model was used, in which the computational area is defined as a space designated by a steady surface and a variable height. Conducted in Nowy Sącz (Poland) experiment confirmed the possibility of using this type of model to diagnose and possibly forecasting ozone concentrations in any area of ​​calculation. The study also showed that the quality of the results depends mainly on accuracy in preparing of input data, …

Alternative Tilings For Improved Surface Area Estimates By Local Counting Algorithms, Erik Learned-Miller

Erik G Learned-Miller

In this paper, we first review local counting methods for perimeter estimation of piecewise smooth binary figures on square, hexagonal, and triangular grids. We verify that better perimeter estimates, using local counting algorithms, can be obtained using hexagonal or triangular grids. We then compare surface area estimates using local counting techniques for binary three-dimensional volumes under the three semi-regular polyhedral tilings: the cubic, truncated octahedral, and rhombic dodecahedral tilings. It is shown that for surfaces of random orientation with a uniform distribution, the expected error of surface area estimates is smaller for the truncated octahedral and rhombic dodecahedral tilings than …

Scale Space Technique For Word Segmentation In Handwritten Manuscripts, R. Manmatha, Nitin Srimal

R. Manmatha

Indexing large archives of historical manuscripts, like the papers of George Washington, is required to allow rapid perusal by scholars and researchers who wish to consult the original manuscripts. Presently, such large archives are indexed manually. Since optical character recognition (OCR) works poorly with handwriting, a scheme based on matching word images called word spotting has been suggested previously for indexing such documents. The important steps in this scheme are segmentation of a document page into words and creation of lists containing instances of the same word by word image matching.

We have developed a novel methodology for segmenting handwritten …

Multimedia Information Retrieval At The Center For Intelligent Information Retrieval, R. Manmatha

R. Manmatha

Building the digital libraries of the future will require a number of different component technologies including the ability to retrieve multi-media information. This paper will describe progress in this area at the Center for Intelligent Information Retrieval (CIIR). This includes: 1) Multi-modal retrieval using appearance based image retrieval and text retrieval. This work has been applied to a large database of trademarks containing image and text data from the US Patent and Trademark Office. 68,000 trademarks may be searched using either image retrieval or image and text retrieval while 615,000 trademarks may be searched using text retrieval. 2) Indexing handwritten …

Optimization Methods For Logical Inference, Vijay Chandru, John Hooker

John Hooker

No abstract provided.

Time Course Of Fmri-Activation In Language And Spatial Networks During Sentence Comprehension, Patricia A. Carpenter, Marcel Adam Just, Timothy A. Keller, William F. Eddy, Keith R. Thulborn

Marcel Adam Just

No abstract provided.

Plasticity Of Language-Related Brain Function During Recovery From Strok, Keith R. Thulborn, Patricia A. Carpenter, Marcel Adam Just

Marcel Adam Just

No abstract provided.

Computational Modeling Of High-Level Cognition And Brain Function, Marcel Adam Just, Patricia A. Carpenter, Sashank Varma

Marcel Adam Just

No abstract provided.

Indexing Flower Patent Images Using Domain Knowledge, Madirakshi Das, R. Manmatha, Edward M. Riseman

R. Manmatha

A new approach to indexing a specialized database by utilizing the color and spatial domain knowledge available for the database is described. This approach is illustrated by using it to provide a solution to the problem of indexing images of flowers for searching a flower patents database by color. The flower region is isolated from the background by using an automatic iterative segmentation algorithm with domain knowledge-driven feedback. The color of the flower is defined by the color names present in the flower region and their relative proportions. The database can be queried by example and by color names. The …

Multi-Modal Retrieval Of Trademark Images Using Global Similarity, S Ravela, R. Manmatha

R. Manmatha

In this paper a system for multi-modal retrieval of trademark images is presented. Images are characterized and retrieved using associated text and visual appearance. A user initiates retrieval for similar trademarks by typing a text query. Subsequent searches can be performed by visual appearance or using both appearance and text information. Textual information associated with trademarks is searched using the INQUERY search engine. Images are searched visually using a method for global image similarity by appearance developed in this paper. Images are filtered with Gaussian derivatives and geometric features are computed from the filtered images. The geometric features used here …