초록 ▼

The subject system provides reduced-dimension mapping of pattern data. Mapping is applied through conventional single-hidden-layer feed-forward neural network with non-linear neurons. According to one aspect of the present invention, the system functions to equalize and orthogonalize lower dimension

The subject system provides reduced-dimension mapping of pattern data. Mapping is applied through conventional single-hidden-layer feed-forward neural network with non-linear neurons. According to one aspect of the present invention, the system functions to equalize and orthogonalize lower dimensional output signals by reducing the covariance matrix of the output signals to the form of a diagonal matrix or constant times the identity matrix. The present invention allows for visualization of large bodies of complex multidimensional data in a relatively "topologically correct" low-dimension approximation, to reduce randomness associated with other methods of similar purposes, and to keep the mapping computationally efficient at the same time.

대표청구항 ▼

[ Having thus described the invention, it is now claimed:] [1.] A system for organizing multi-dimensional pattern data into a reduced-dimension representation comprising:a neural network comprised of a plurality of layers of nodes, the plurality of layers including:an input layer comprised of a plur

[ Having thus described the invention, it is now claimed:] [1.] A system for organizing multi-dimensional pattern data into a reduced-dimension representation comprising:a neural network comprised of a plurality of layers of nodes, the plurality of layers including:an input layer comprised of a plurality of input nodes,a hidden layer, andan output layer comprised of a plurality of non-linear output nodes, wherein the number of non-linear output nodes is less than the number of input nodes;receiving means for receiving multi-dimensional pattern data into the input layer of the neural network;output means for generating an output signal for each of the output nodes of the output layer of the neural network corresponding to received multi-dimensional pattern data; andtraining means for completing a training of the neural network, wherein the training means includes means for equalizing and orthogonalizing the output signals of the output nodes by reducing a covariance matrix of the output signals to the form of a diagonal matrix.