Title :
DENDRITE: A system for visual interpretation of neural network data
Author :
Jones, Warren T. ; Vachha, Rustom K. ; Kulshrestha, Anil P.
Author_Institution :
Dept. of Comput. & Inf. Sci., Alabama Univ., Birmingham, AL, USA
Abstract :
DENDRITE is a visualization system being developed that helps interpret neural network (NN) data. DENDRITE´s design consists of three overlapping modules: the graphical representation of the network: the interface between the NN simulation, the representation of the analyzed data, and the NN itself; and data analysis. The backpropagation algorithm was selected to train the network. The graphical representation aids the researcher in visually perceiving the dynamic nature of the network as it is being trained with a given configuration and data. The system basically consists of a graphical user interface with a toolkit that contains primitives to build a neural network, and an interface to a library of mathematical and statistical functions
Keywords :
backpropagation; data analysis; data visualisation; graphical user interfaces; neural nets; virtual machines; DENDRITE; NN simulation; analyzed data; backpropagation algorithm; data analysis; graphical representation; graphical user interface; neural network data; statistical functions; visual interpretation; Artificial neural networks; Biological system modeling; Biology computing; Computational modeling; Computer networks; Data analysis; Libraries; Network topology; Neural networks; Scientific computing;
Conference_Titel :
Southeastcon '92, Proceedings., IEEE
Conference_Location :
Birmingham, AL
Print_ISBN :
0-7803-0494-2
DOI :
10.1109/SECON.1992.202274
