Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Marijke F. Augusteijn"'
Publikováno v:
Pattern Analysis & Applications. 3:153-168
The problem of word spotting in handwritten archives is approached by matching global shape features. A set of visual templates is used to define the keyword class of interest, and initiate a search for words exhibiting high shape similarity to the m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6fb3eea83828f1d0e968b0704157868d
https://doi.org/10.1007/s100440070020
https://doi.org/10.1007/s100440070020
Autor:
Kelly A. Shaw, Marijke F. Augusteijn
Publikováno v:
International Journal of Neural Systems. 10:143-154
Trained radial basis function networks are well-suited for use in extracting rules and explanations because they contain a set of locally tuned units. However, for rule extraction to be useful, these networks must first be pruned to eliminate unneces
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e4c477ce9893354d90da09367b0a8719
https://doi.org/10.1142/s0129065700000120
https://doi.org/10.1142/s0129065700000120
Publikováno v:
International Journal of Remote Sensing. 20:1987-2002
This study investigates whether combining several different image classifications together with an a priori image model of the expected spatial distribution of the classes can produce a better classification. A maximum likelihood classifier and the c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::059188341ef4c4a773c266c9e980e0db
https://doi.org/10.1080/014311699212308
https://doi.org/10.1080/014311699212308
Autor:
Marijke F. Augusteijn, U. J. Steck
Publikováno v:
Neural Computing & Applications. 7:78-89
A neural network architecture is introduced which implements a supervised clustering algorithm for the classification of feature vectors. The network is selforganising, and is able to adapt to the shape of the underlying pattern distribution as well
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f0c98ddd5ecb4e11cda373138a0f5264
https://doi.org/10.1007/bf01413712
https://doi.org/10.1007/bf01413712
Publikováno v:
Neural Computing & Applications. 4:209-217
A method is described to extract an index from a binary character image for database storage and retrieval. The index is hierarchical in nature, and different parts can retrieve character image clusters of different sizes. A hierarchy of Kohonen neur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::17b553a1ae9a89f5cb3de2db87fa422f
https://doi.org/10.1007/bf01413819
https://doi.org/10.1007/bf01413819
Publikováno v:
Engineering Applications of Artificial Intelligence. 9:75-81
A neural-network architecture is used here to find boundaries between differently textured surfaces in an image. The architecture is trained on boundaries between a specific set of textures and is shown to be able to generalize its training to other
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f4398cb30dd377454bf87d792ba27c19
https://doi.org/10.1016/0952-1976(95)00067-4
https://doi.org/10.1016/0952-1976(95)00067-4
Autor:
Joseph M. Hill, Marijke F. Augusteijn
Publikováno v:
Neural Computing & Applications. 3:17-26
The possibility to use neural networks to guide animated motion sequences is investigated. The performance of two recurrent architectures, both derived from the cascade-correlation network, is compared. These architectures only differ in the objectiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ab12f2c2cb95cb717fb0f689d8ce030f
https://doi.org/10.1007/bf01414173
https://doi.org/10.1007/bf01414173
Publikováno v:
Telematics and Informatics. 9:131-144
This article describes a study of the feasibility of automated classification of satellite images. Satellite images were characterized by the textures they contain. In particular, the detection of cloud textures was investigated. The method of second
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa196df582df9d070349d6b480d0bb55
https://doi.org/10.1016/s0736-5853(05)80031-0
https://doi.org/10.1016/s0736-5853(05)80031-0
Autor:
Kelly A. Shaw, Marijke F. Augusteijn
Publikováno v:
International journal of neural systems. 12(3-4)
Artificial neural networks will be more widely accepted as standard engineering tools if their reasoning process can be made less opaque. This paper describes NetQuery, an explanation mechanism that extracts meaningful explanations from trained Radia
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24418073d07258f81fb5c89115a38c4d
https://pubmed.ncbi.nlm.nih.gov/12370959
https://pubmed.ncbi.nlm.nih.gov/12370959
Autor:
Kelly A. Shaw, Marijke F. Augusteijn
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783540673545
MICAI
MICAI
Artificial neural networks will be more widely accepted as standard engineering tools if their reasoning process can be made less opaque. This paper describes NetQuery, an explanation mechanism that extracts explanations from trained Radial Basis Fun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c628df19ad9b843d57e336cce9746bc
https://doi.org/10.1007/10720076_34
https://doi.org/10.1007/10720076_34
