Svoboda | Graniru | BBC Russia | Golosameriki | Facebook
Skip to main content
Geachte aanwezigen, op het moment dat ik deze rede uitspreek, realiseer ik me goed dat de naam van mijn leerstoel, Kunstmatige Intelligentie, een intrinsieke tegenstrijdigheid zou kunnen bevatten. Immers, na vijftig jaar onderzoek is het... more
Geachte aanwezigen, op het moment dat ik deze rede uitspreek, realiseer ik me goed dat de naam van mijn leerstoel, Kunstmatige Intelligentie, een intrinsieke tegenstrijdigheid zou kunnen bevatten. Immers, na vijftig jaar onderzoek is het nog steeds niet duidelijk of de mensheid in staat zal zijn om een kunstmatig systeem te construeren dat onze wereld kan waarnemen en begrijpen, om vervolgens ook intelligent te handelen.
ABSTRACT
How do we select combinations of limb segments to carry out physical tasks? Three possible determinants of limb-segment selection are hypothesized here: (1) optimal amplitudes and frequencies of motion for the effectors; (2) preferred... more
How do we select combinations of limb segments to carry out physical tasks? Three possible determinants of limb-segment selection are hypothesized here: (1) optimal amplitudes and frequencies of motion for the effectors; (2) preferred movement axes for the effectors; and (3) a tendency to continue using already-recruited limb-segments. We tested these factors in a graphic production task. Seven subjects produced back-and-forth drawing movements of gradually changing amplitude. The largest amplitude to be covered, trial duration, movement axis, and direction of amplitude change (from small to large or vice versa) were varied between trials. Selspot recordings were used to study the relative contributions of the fingers, hand, and arm to displacements of the pen. The temporal order of limb-segment involvement was also studied. The results confirmed the predicted effects of the three limb-segment selection factors. We conclude that limb-segment coordination is adaptively related to biomechanical features of the motor system and to the computational demands of movement selection itself.
T his raises the q uestion: what is inte llig ent b ehaviour, and how does it work? M a yb e the easiest answer is that inte llig ence is ap ro p ert y of humans and other life forms. M ost p eo ple seem to have a common im plicit... more
T his raises the q uestion: what is inte llig ent b ehaviour, and how does it work? M a yb e the easiest answer is that inte llig ence is ap ro p ert y of humans and other life forms. M ost p eo ple seem to have a common im plicit understandin g of what this p ro p ert y'inte lli g ence'is and what kinds of b ehaviour it b rin g sa b out. H owever, it is ex treme ly diffi cu lt, or ma yb e even im p ossible, to forma lly de fi ne the conce pt of inte llig ence in a satisfactor y wa y. T o understand what it is, we stud y inte llig ence as it manifests itse lf in the livin gb ein gs ...
Support vector machines (SVMs) are very popular methods for solving classification problems that require mapping input features to target labels. When dealing with real-world data sets, the different classes are usually not linearly... more
Support vector machines (SVMs) are very popular methods for solving classification problems that require mapping input features to target labels. When dealing with real-world data sets, the different classes are usually not linearly separable, and therefore support vector machines employ a particular kernel function. Such a kernel function computes the similarity between two input patterns, but has as drawback that all input dimensions are considered equally important for computing this similarity. In this paper we propose a ...
Goal of the dScript system is 1) to promote handwriting recognition in general, 2) to demonstrate our handwriting expertise in a real application. As such, our system has been a great succes. Two versions of the system have been on... more
Goal of the dScript system is 1) to promote handwriting recognition in general, 2) to demonstrate our handwriting expertise in a real application. As such, our system has been a great succes. Two versions of the system have been on display at different museums in The Netherlands. Visitors of these museums have shown a large interest in using the system, even when the dScript makes some recognition mistakes.
This short technical report informally describes some basic ideas for a command language that naturally incorporates the asynchronous nature of events in the users' working environment. The general idea, system components and problem... more
This short technical report informally describes some basic ideas for a command language that naturally incorporates the asynchronous nature of events in the users' working environment. The general idea, system components and problem areas are dealt with briefly. Many concrete examples of the language syntax are given.
Data from a heterogeneous writer population were divided over the writer style categories mixed, cursive and handprint. Two components of the on-line word recognition system developed at the NICI 2, 1] were specialized on each of the... more
Data from a heterogeneous writer population were divided over the writer style categories mixed, cursive and handprint. Two components of the on-line word recognition system developed at the NICI 2, 1] were specialized on each of the three styles: the Kohonen stroke network representing strokes, and the transition network representing occurrences of sequences of strokes. The top-word recognition performance of these specialized agents was compared to that of a recognizer trained on all data (a lumped recognizer). The ...
Search all the public and authenticated articles in CiteULike. Include unauthenticated results too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id (123456),. a DOI (doi:10.1234/12345678).... more
Search all the public and authenticated articles in CiteULike. Include unauthenticated results too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id (123456),. a DOI (doi:10.1234/12345678). or a PubMed ID (pmid:12345678). Click Help for advanced usage. CiteULike, Group: handwriting-recognition, Search, Register, Log in, ...
Search all the public and authenticated articles in CiteULike. Include unauthenticated results too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id (123456),. a DOI (doi:10.1234/12345678).... more
Search all the public and authenticated articles in CiteULike. Include unauthenticated results too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id (123456),. a DOI (doi:10.1234/12345678). or a PubMed ID (pmid:12345678). Click Help for advanced usage. CiteULike, Group: handwriting-recognition, Search, Register, Log in, ...
Geachte aanwezigen, op het moment dat ik deze rede uitspreek, realiseer ik me goed dat de naam van mijn leerstoel, Kunstmatige Intelligentie, een intrinsieke tegenstrijdigheid zou kunnen bevatten. Immers, na vijftig jaar onderzoek is het... more
Geachte aanwezigen, op het moment dat ik deze rede uitspreek, realiseer ik me goed dat de naam van mijn leerstoel, Kunstmatige Intelligentie, een intrinsieke tegenstrijdigheid zou kunnen bevatten. Immers, na vijftig jaar onderzoek is het nog steeds niet duidelijk of de mensheid in staat zal zijn om een kunstmatig systeem te construeren dat onze wereld kan waarnemen en begrijpen, om vervolgens ook intelligent te handelen.
at this moment in time, I realize clearly that the name of my chair, ie, Artificial Intelligence, may contain an intrinsic contradiction. Indeed, after fifty years of research, it is still not clear whether humanity will be able to... more
at this moment in time, I realize clearly that the name of my chair, ie, Artificial Intelligence, may contain an intrinsic contradiction. Indeed, after fifty years of research, it is still not clear whether humanity will be able to construct an artificial system which can perceive our world and understand it, in order to display intelligent behaviour consequently.
To read minds has long been man's great desire. Opinions differ on whether this will ever be possible, be it by machines or humans. Though there exists abundant philosophical dispute about whether or not it is possible in principle,... more
To read minds has long been man's great desire. Opinions differ on whether this will ever be possible, be it by machines or humans. Though there exists abundant philosophical dispute about whether or not it is possible in principle, time must tell whether this ambitious goal will ever be attained. In this thesis I pursue a simplified version of mind reading. Recent findings have led us to believe it is possible to discern several different cognitive states 1 from recordings of neural activity. During this research I try to obtain similar results. The ultimate ...
Uit de geschiedenis van de psychologie valt op te maken dat er een sterke wisselwerking bestaat tussen de stand van de techniek en de modelvorming binnen die psychologie. Meestal beınvloedt de techniek de wijze van denken binnen de... more
Uit de geschiedenis van de psychologie valt op te maken dat er een sterke wisselwerking bestaat tussen de stand van de techniek en de modelvorming binnen die psychologie. Meestal beınvloedt de techniek de wijze van denken binnen de psychologie (Vroon en Draaisma, 1986). Soms treedt echter ook het omgekeerde op: terwijl de Gestalttheorie bij de behavioristen in diskrediet was geraakt, werd deze herontdekt door onderzoekers die bezig waren met automatische beeldherkenning. De robotica is een aspect van de techniek dat ...
Search all the public and authenticated articles in CiteULike. Include unauthenticated results too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id (123456),. a DOI (doi:10.1234/12345678).... more
Search all the public and authenticated articles in CiteULike. Include unauthenticated results too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id (123456),. a DOI (doi:10.1234/12345678). or a PubMed ID (pmid:12345678). Click Help for advanced usage. CiteULike, Group: handwriting-recognition, Search, Register, Log in, ...
Search all the public and authenticated articles in CiteULike. Include unauthenticated results too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id (123456),. a DOI (doi:10.1234/12345678).... more
Search all the public and authenticated articles in CiteULike. Include unauthenticated results too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id (123456),. a DOI (doi:10.1234/12345678). or a PubMed ID (pmid:12345678). Click Help for advanced usage. CiteULike, Group: computer-go, Search, Register, Log in, ...
This study is concerned with the processes that take place from the moment that a writer wants to write down a given word, until he or she can inspect the finished result. What types of transformation are needed, going from planned word... more
This study is concerned with the processes that take place from the moment that a writer wants to write down a given word, until he or she can inspect the finished result. What types of transformation are needed, going from planned word to muscle contraction? Which components of writing behavior are explicitly planned, and which components are emergent consequences of neural or biomechanical processes? The goal of this thesis is to enlighten at least to some extent these intriguing but hard-to-solve questions. The approach ...
Abstract There are at least two major stumbling blocks for user acceptance of pen-based computers: the recognition performance is not good enough, especially on cursive handwriting; and the user interface technology has not reached a... more
Abstract There are at least two major stumbling blocks for user acceptance of pen-based computers: the recognition performance is not good enough, especially on cursive handwriting; and the user interface technology has not reached a mature stage. The initial reaction of product reviewers and potential user groups to pen-based computers varies. The realistic assessment is that this is a technology with a large potential, but still too brittle for serious real-world use. The author focuses on user interface aspects of handwriting ...
DSpace,  Search Radboud Repository. Advanced Search. ...
The human reader of handwriting is unaware of the amount of back-ground knowledge that is constantlybeing used by a massive parallel computer, his brain, to decipher cursive script. Artificial cursive scriptrecognizers do not have access... more
The human reader of handwriting is unaware of the amount of back-ground knowledge that is constantlybeing used by a massive parallel computer, his brain, to decipher cursive script. Artificial cursive scriptrecognizers do not have access to a comparable source of knowledge or of comparable computational powerto perform top-down processing. Therefore, in an artificial script recognizer, there is a strong demand
Intelligent Information Retrieval and Presentation with Multimedia Databases Floris Wiesman IKAT, Universiteit Maastricht PO Box 616, 6200 MD Maastricht, The Netherlands wiesman@ cs. unimaas. nl Stefano Bocconi Centrum voor Wiskunde en... more
Intelligent Information Retrieval and Presentation with Multimedia Databases Floris Wiesman IKAT, Universiteit Maastricht PO Box 616, 6200 MD Maastricht, The Netherlands wiesman@ cs. unimaas. nl Stefano Bocconi Centrum voor Wiskunde en Informatica PO Box 94079, ...
The Borda count is a simple yet effective method of combining rankings. In pattern recognition, classifiers are often able to return a ranked set of results. Several experiments have been conducted to test the ability of the Borda count... more
The Borda count is a simple yet effective method of combining rankings. In pattern recognition, classifiers are often able to return a ranked set of results. Several experiments have been conducted to test the ability of the Borda count and two variant methods to combine these ranked classifier results. By using artificial data, domain-specific results were avoided. The results show the strength of the Borda count when many errors occur in the results, but also show its weakness in case of a limited number of large ranking errors.
Abstract The paper introduces a variant of agglomerative hierarchical clustering techniques. The new technique is used for categorizing character shapes (allographs) in large data sets of handwriting into a hierarchical structure. Such a... more
Abstract The paper introduces a variant of agglomerative hierarchical clustering techniques. The new technique is used for categorizing character shapes (allographs) in large data sets of handwriting into a hierarchical structure. Such a technique may be used as the basis for a systematic naming scheme of character shapes. Problems with existing methods are described and the proposed method is explained. After application of the method to a very large set of characters, separately for all the letters of the alphabet, relevant clusters are ...
This paper first summarizes a number of findings in human reading of handwriting. A method is proposed to uncover more detailed information about geometrical features which human readers use in the reading of Western script. The results... more
This paper first summarizes a number of findings in human reading of handwriting. A method is proposed to uncover more detailed information about geometrical features which human readers use in the reading of Western script. The results of an earlier experiment on the use of ascender/descender features were used for a second experiment aimed at more detailed features within words. A convenient experimental setup was developed, based on image enhancement by local mouseclicks under time pressure. The readers had to develop a ...
Research Interests:
Research Interests:
Search all the public and authenticated articles in CiteULike. Include unauthenticated results too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id (123456),. a DOI... more
Search all the public and authenticated articles in CiteULike. Include unauthenticated results too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id (123456),. a DOI (doi:10.1234/12345678). or a PubMed ID (pmid:12345678). Click Help for advanced usage. CiteULike, Group: handwriting-recognition, Search, Register, Log in, ...
Research Interests:
Research Interests:
Research Interests:
Data from a heterogeneous writer population were divided over the writer style categories mixed, cursive and handprint. Two components of the on-line word recognition system developed at the NICI 2, 1] were specialized on each of the... more
Data from a heterogeneous writer population were divided over the writer style categories mixed, cursive and handprint. Two components of the on-line word recognition system developed at the NICI 2, 1] were specialized on each of the three styles: the Kohonen stroke network representing strokes, and the transition network representing occurrences of sequences of strokes. The top-word recognition performance of these specialized agents was compared to that of a recognizer trained on all data (a lumped recognizer). The ...
Research Interests:

And 137 more