Pre-Grant Publication Number: 20090132452
View Prior Art submitted by the community. You can see full text, rate and annotate the Prior Art by clicking on
any of the listed Prior Art references. You can also click on the name of the person who submitted art to view their profile
and any other Prior Art they have previously submitted.
How to Rate Prior ArtRating Prior Art - Click the thumbs up or down to indicate if a submission is relevant enough to the claims of the application to
deserve a spot in the Top 10 submissions that will be forwarded to the patent examiner. Rating should be based only on relevance.
For an explanation of prior art, please visit the Tutorial Page. Annotations(0)
Patent/Application # 6581049
Artificial neuron for artificial intelligence system, has multiple dendrites with power series of weights having associated counts for associated powers.
Patent/Application # 6625588
Associative neuron for artificial neural network - forms sum of received auxiliary input signals weighted by coefficients, and applies non-linear function to weighted sum to generate non-linear signal.
Title Proceedings of the International Joint Conference on Neural Networks (IJCNN 2002)
Abstract: We present a generalization of conventional artificial neural networks that allows for a functional equivalence to multi-expert systems. The new model provides an architectural freedom going beyond existing multi-expert models and an integrative formalism to compare and combine various techniques of learning. (We consider gradient, EM, reinforcement, and unsupervised learning.) Its uniform representation aims at a simple genetic encoding and evolutionary structure optimization of multi-expert systems. This paper contains a detailed description of the model and learning rules, empirically validates its functionality, and discusses future perspectives.
Patent/Application # 7287015
"Signal transmission method for classification system, involves extracting functional and membership components from input signal "