Designs for cognitive memory systems storing input data, images, or patterns, and retrieving it without knowledge of where stored when cognitive memory is prompted by query pattern that is related to sought stored pattern. Retrieval system of cognitive memory uses autoassociative neural networks and techniques for pre-processing query pattern to establish relationship between query pattern and sought stored pattern, to locate sought pattern, and to retrieve it and ancillary data. Cognitive memory, when connected to computer or information appliance introduces computational architecture that applies to systems and methods for navigation, location and recognition of objects in images, character recognition, facial recognition, medical analysis and diagnosis, video image analysis, and to photographic search engines that when prompted with a query photograph containing faces and objects will retrieve related photographs stored in computer or other information appliance, and will identify URL's of related photographs and documents stored on the World Wide Web.
RELATED APPLICATIONS
This application claims priority to U.S. Provisional Patent Application Ser. No. 60/617,245 filed Oct. 7, 2004, entitled "A Cognitive Memory", which is hereby incorporated by reference. U.S. patent application Ser. No. 11/145,861, filed 7 Oct. 2005 entitled System And Method For Cognitive Memory And Auto Associative Neural Network Based Pattern Recognition is also a related application.
The invention relates to a method for the computer-supported generation of prognoses for operative systems (37), in particular for control processes and similar, based on multi-dimensional data sets describing a system, product and/or process condition, using the SOM method in which an ordered grid of nodes (1), representing the data distribution is determined and an internal scaling (.sigma..sub.j) of variables (x.sub.j) with regard to non-linearity in the data, based on the non-linear influence of each variable on the prognosis variable, is carried out. Local receptive regions corresponding to the nodes (1) are determined, on the basis of which local linear regressions are calculated. Using the number of local prognosis models obtained thus, optimized prognosis values for the control of the operative system (37) are calculated, whereby for each new data set the relevant sufficient nodes are determined and the local prognosis model applied to this data set.
In a method of 3D object detection, a learning procedure is used for feature selection from a feature set based on an annotated image-volume database, generating a set of selected features. A classifier is built using a classification scheme to distinguish between an object location and a non-object location and using the set of selected features. The classifier is applied at a candidate volume to determine whether the candidate volume contains an object of interest.
