Data processing: artificial intelligence – Neural network – Learning method
Reexamination Certificate
2006-05-08
2008-11-18
Starks, Jr., Wilbert L (Department: 2129)
Data processing: artificial intelligence
Neural network
Learning method
C706S045000
Reexamination Certificate
active
07454388
ABSTRACT:
A discovery system employing a neural network, training within this system, that is stimulated to generate novel output patterns through various forms of perturbation applied to it, a critic neural network likewise capable of training in situ within this system, that learns to associate such novel patterns with their utility or value while triggering reinforcement learning of the more useful or valuable of these patterns within the former net. The device is capable of bootstrapping itself to progressively higher levels of adaptive or creative competence, starting from no learning whatsoever, through cumulative cycles of experimentation and learning. Optional feedback mechanisms between the latter and former self-learning artificial neural networks are used to accelerate the convergence of this system toward useful concepts or plans of action.
REFERENCES:
patent: 5640494 (1997-06-01), Jabri et al.
patent: 5659666 (1997-08-01), Thaler
patent: 5692107 (1997-11-01), Simoudis et al.
patent: 5845271 (1998-12-01), Thaler
patent: 5852815 (1998-12-01), Thaler
patent: 5852816 (1998-12-01), Thaler
patent: 6014653 (2000-01-01), Thaler
patent: 6018727 (2000-01-01), Thaler
patent: 6115701 (2000-09-01), Thaler
patent: 6169981 (2001-01-01), Werbos
patent: 6356884 (2002-03-01), Thaler
patent: 02/063555 (2002-08-01), None
Stefan, P., Combined use of Reinforcement Learning and Simulated Annealing: Algorithms and Applications, Ph.D. Thesis, University of Miskolc, Dept. of Mechanical Engineering, 2003, pp. 1-119.
Thathachar, M., et al., Global Boltzmann Perceptron Network for On-line Learning of Conditional Distributions, IEEE Transactions on Neural Networks, vol. 10, No. 5, Sep. 1999, pp. 1090-1098.
Rubtsov, D. V. et al., “XML Based Format For Trained Neural Network Definition”, Academic Open Internet Journal, vol. 4, 2001, pp. 1-7.
Marrone, P., “The Complete Guide—All You Need to Know About Joone”, Feb. 2005, pp. 1-137.
Mayer, Helmut A., A Modular Neurocontroller for Creative Mobile Autonomous Robots Learning by Temporal Difference, Department of Scientific Computing, University of Salzburg, A-5020 Salzburg, Austria.
Thaler, S., “The Emerging Intelligence and Its Critical Look at Us”, Journal of Near-Death Studies, vol. 17, No. 1, 1998, pp. 21-29.
Thaler, S., “A Quantitative Model of Seminal Cognition: The Creativity Machine Paradigm”, XP002445582, 1997, p. 1-3.
Thaler, S., “Self-Training Artificial Neural Networks: Nets, Spreadsheets, and Objects”, PC AI, vol. 10, 1996, pp. 32-34.
Thaler, S., “Predicting ultra-hard binary compounds via cascaded auto- and hetero-associative neural networks”, Journal of Alloys and Compounds, vol. 279, No. 1, 1998, pp. 47-59.
PCT International Search Report for PCT/US2006/017731.
Tan, Ah-Hwee, “Learning user profiles for personalized information dissemination”, IEEE, vol. 1, 1998, pp. 183-188.
PHYSTA Report 2.4: “Generation of subsymbolic representations in the emotion understanding problem”, XP002442963, 2000, pp. 1-57.
Cogan, B., “The power of neural networks”, Scientific Computing World, XP002449470, 2003, pp. 1-2.
Press Release, “NeuroIntelligence 2.2 Released”, Alyuda Research Company, XP002449471, 2005, p. 1.
PCT International Search Report for PCT/US2006/028591.
Husch Blackwell Sanders LLP
Rusche H. Frederick
Starks, Jr. Wilbert L
LandOfFree
Device for the autonomous bootstrapping of useful information does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Device for the autonomous bootstrapping of useful information, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Device for the autonomous bootstrapping of useful information will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4034997