DocumentCode
296169
Title
Visualization of neural networks using saliency maps
Author
Morch, Niels J S ; Kjems, Ulrik ; Hansen, Lars Kai ; Svarer, Claus ; Law, Ian ; Lautrup, Benny ; Strother, Steve ; Rehm, Kelly
Author_Institution
Electron. Inst., Tech. Univ., Lyngby, Denmark
Volume
4
fYear
1995
fDate
Nov/Dec 1995
Firstpage
2085
Abstract
The saliency map is proposed as a new method for understanding and visualizing the nonlinearities embedded in feedforward neural networks, with emphasis on the ill-posed case, where the dimensionality of the input-field by far exceeds the number of examples. Several levels of approximations are discussed. The saliency maps are applied to medical imaging (PET-scans) for identification of paradigm-relevant regions in the human brain
Keywords
feedforward neural nets; learning (artificial intelligence); medical image processing; positron emission tomography; PET-scans; dimensionality; feedforward neural networks; human brain; ill-posed case; medical imaging; paradigm-relevant regions; saliency maps; visualization; Biological neural networks; Biomedical imaging; Biomedical informatics; Fingers; Geometry; Humans; Neural networks; Positron emission tomography; Visualization; Volume measurement;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location
Perth, WA
Print_ISBN
0-7803-2768-3
Type
conf
DOI
10.1109/ICNN.1995.488997
Filename
488997
Link To Document