R. Hanka, T. P. Harte, Curse of dimensionality: Classifying large multi--dimensional images with neural networks, in: Proceedings of the European Workshop on Computer-- Intensive Methods in Control and Signal Processing (CIMCSP1996. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Number Theoretic Transforms in Neural Network Image.. - Harte, Hanka (1997) (1 citation) Self-citation (Hanka Harte) (Correct)
.... network classifier of tissue in magnetic resonance images (MRI) 3] We have presented an FFT based speed up algorithm, where we observed that when an image mask forms the input to feed forward neural networks, such as the multi layer perceptron, the underlying operation is spatial convolution [4]. We achieve this multi dimensional convolution via the FFT. Much effort of the VLSI community has been placed into ensuring that floating point arithmetic, upon which the FFT relies, is nowadays blindingly fast compared to the hardware of yesteryear. However, integer multiplication is simpler ....
....the input stage of the neural network alone. It would seem that mask processing is not computationally feasible, considering the time constraints required for a clinical application. We achieve significant computational economy by showing that mask processing in this context is spatial convolution [4]. Observe that the inner product in Eq. 2) is conventionally written in 1 D array terms [2, Page 118] but, for mask processing, a hyper cube forms the input to the first hidden layer. Thus, we write the x s and w s as functions of the hyper cubic image indices, e.g. x(n 0 ; n 1 ; n 2 ; n 3 ) As ....
[Article contains additional citation context not shown here]
R. Hanka and T.P. Harte. Curse of dimensionality: classifying large multi-dimensional images with neural networks. In Computer-Intensive Methods in Control and Signal Processing , K. Warwick and M. K'arn'y (Ed.s), Birkhauser Boston, New York, 1997, pp. 249--260.
Automated machine recognition of lesions in dynamic.. - Harte, Lomas, Dixon.. Self-citation (Hanka) (Correct)
....exhaustively classifies the entire dynamic MR image set. Additionally, the classifier must operate under real time conditions, where real time is bounded by minutes, if it is to be of practical benefit. Real time neural network classification of large image data sets have been proposed elsewhere [18,20 21]. The two principal limiting factors in this analysis were identified as follows. Firstly, the assessment of error in the classifier s performance is difficult as pixel by pixel labelling of the test data is not available, nor is it feasible. Although all of the pre established tissue types were ....
Hanka R, Harte TP, Curse of dimensionality: classifying large multi-dimensional images with neural networks. Warwick K, K'arn'y M, editors, Computer-Intensive Methods in Control and Signal Processing: The Curse of Dimensionality, Birkhauser Boston, 1997:249--260.
A Review of Content-Based Image Retrieval Systems.. - Müller, Michoux.. (Correct)
No context found.
R. Hanka, T. P. Harte, Curse of dimensionality: Classifying large multi--dimensional images with neural networks, in: Proceedings of the European Workshop on Computer-- Intensive Methods in Control and Signal Processing (CIMCSP1996.
Detection of Malignancy Associated Changes in Cervical Cells.. - Hallinan (1999) (Correct)
No context found.
Hank, R. & Harte, T. P. 1997, `Curse of dimensionality: Classifying large multi-dimensional images with neural networks', in Warwick, K. & Krn, M. (ed), 1997, Computer-Intensive Methods in Control and Signal Processing: The Curse of Dimensionality, Birkhuser, Boston.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC