Data processing: artificial intelligence – Machine learning
Reexamination Certificate
2006-09-26
2009-11-17
Vincent, David R (Department: 2129)
Data processing: artificial intelligence
Machine learning
Reexamination Certificate
active
07620607
ABSTRACT:
A system for generating annotations of a document, including a plurality of neurons connected as a neural network, the neurons being associated with words, sentences and documents. An activity regulator regulates a minimum and/or maximum number of neurons of the neural network that are excited at any given time. The neurons are displayed to a user and identify the neurons that correspond to sentences containing a predetermined percentage of document meaning. The annotations can be also based on a context of the user's search query. The query can include keywords, documents considered relevant by the user, or both. Positions of the neurons relative to each other can be changed on a display device, based on input from the user, with the change in position of one neuron changing the resulting annotations. The input from the user can also include changing a relevance of neurons relative to each other, or indicating relevance or irrelevance of a document or sentence.
REFERENCES:
patent: 5937084 (1999-08-01), Crabtree et al.
patent: 6615197 (2003-09-01), Chai
patent: 6633868 (2003-10-01), Min et al.
patent: 6999959 (2006-02-01), Lawrence et al.
patent: 7584175 (2009-09-01), Patterson
patent: 2002/0174101 (2002-11-01), Fernley et al.
patent: 2004/0172378 (2004-09-01), Shanahan et al.
patent: 2005/0165747 (2005-07-01), Bargeron et al.
patent: 2006/0294094 (2006-12-01), King et al.
patent: 2007/0022068 (2007-01-01), Linsker
Nejad, A & Gedeon, T. “Bidirectional Neural Network and Class Prototypes”, IEEE Conf. Neural Networks, 1995, pp. 1322-1327.
Yusoff “Artificial Neural Networks (ANN) and Its Application in Engineering”, http://ppt.ump.edu.my/images/mech/ANN.pdf.
Merkl “Text classification with self-organizing maps: Some lessons learned”, Neurocomputing 21 (1998) pp. 61-77.
Bonnyman et al. “A Neural Network Application for the Analysis and Synthesis of Multilingual Speech”, 1994, SIPNN, pp. 13-16.
Paralic et al. “Text Mining for Documents Annotation and Ontology Support”, http://people.tuke.sk/jan.paralic/papers/BookChapter.pdf.
Brause et al. “Transform Coding by Lateral Inhibited Neural Nets”, Porc. IEEE TAI, 1993, pp. 14-21.
Merkl., “Text classification with self-organizing maps: Some lessons learned”, Neurocomputing 21 (1998) pp. 61-77.
Bloehdorn et al. , “Semantic Annotation of Images and Videos for Multimedia Analysis”, ESWC 2005.
Bardmesser Law Group, P.C.
Chang Li-Wu
Quintura Inc.
Vincent David R
LandOfFree
System and method for using a bidirectional neural network... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for using a bidirectional neural network..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for using a bidirectional neural network... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4107586