Data processing: artificial intelligence – Neural network – Learning task
Patent
1999-08-09
2000-09-05
Hafiz, Tariq R.
Data processing: artificial intelligence
Neural network
Learning task
706 28, 706 30, 706 46, G06F 1518
Patent
active
061157015
ABSTRACT:
A system and process for readily determining, for a specified knowledge domain in a given field of endeavor, perturbations applicable to an artificial neural network embodying such a specified knowledge domain that will produce a desired output, comprising a first, previously trained, artificial neural network containing training in some problem domain, which neural network is responsive to the presentment of a set of data inputs at the input portion thereof to produce a set of data outputs at the output portion thereof, a monitoring portion which constantly monitors the outputs of the first neural network to identify the desired outputs, and a network perturbation portion for effecting the application of perturbations, either externally or internally, to the first neural network to thereby effect changes in the output thereof. The perturbations may be effected by any number of different means, including by, but not limited to, presentment of new, varied data inputs, alteration or fixed or previously applied data inputs, such as by the introduction of noise to the inputs, relaxation or degradation of the network, and so forth, either randomly or systematically, and may be accomplished autonomously or upon specific external authorization or control. Identification of a desired output establishes an input/perturbation/output mapping relationship from which data inputs (external perturbations) and/or knowledge domain alterations (internal perturbations) that produce the desired output can be determined. The system and process can be employed in some instances and in some embodiments as a target seeking system for use with various design or problem solving applications, and can, in some embodiments, comprise or be comprised of a system and process for autonomously producing and identifying desirable design concepts through utilization of such a target seeking system.
REFERENCES:
patent: 4591980 (1986-05-01), Huberman et al.
patent: 4941122 (1990-07-01), Weideman
patent: 5058184 (1991-10-01), Fukushima
patent: 5067095 (1991-11-01), Peterson et al.
patent: 5150450 (1992-09-01), Swenson et al.
patent: 5153923 (1992-10-01), Matsuba et al.
patent: 5155801 (1992-10-01), Lincoln
patent: 5197114 (1993-03-01), Skeirik
patent: 5214715 (1993-05-01), Carpenter et al.
patent: 5226092 (1993-07-01), Chen
patent: 5235673 (1993-08-01), Austvold et al.
patent: 5239593 (1993-08-01), Wittner et al.
patent: 5239594 (1993-08-01), Yoda
patent: 5241620 (1993-08-01), Ruggiero
patent: 5299285 (1994-03-01), Tawel
patent: 5303328 (1994-04-01), Masui et al.
patent: 5303329 (1994-04-01), Mead et al.
patent: 5303330 (1994-04-01), Gersho et al.
patent: 5353207 (1994-10-01), Keeler et al.
patent: 5398300 (1995-03-01), Levey
patent: 5416888 (1995-05-01), Shimokawa
patent: 5422961 (1995-06-01), Simard
patent: 5424959 (1995-06-01), Reyes et al.
patent: 5452400 (1995-09-01), Takahashi et al.
patent: 5465308 (1995-11-01), Hutcheson et al.
patent: 5481481 (1996-01-01), Frey et al.
patent: 5500905 (1996-03-01), Martin et al.
patent: 5581459 (1996-12-01), Enbutsu et al.
patent: 5588091 (1996-12-01), Alkon et al.
patent: 5622171 (1997-04-01), Asada et al.
patent: 5640494 (1997-06-01), Jabri et al.
patent: 5659666 (1997-08-01), Thaler
patent: 5668717 (1997-09-01), Spall
patent: 5692107 (1997-11-01), Simoudis et al.
patent: 5701400 (1997-12-01), Amado
patent: 5729662 (1998-03-01), Rozmus
patent: 5740324 (1998-04-01), Mathur et al.
patent: 5845271 (1998-12-01), Thaler
patent: 5852815 (1998-12-01), Thaler
patent: 5852816 (1998-12-01), Thaler
Eapen, "Neural Network For Underwater Target Detection"; IEEE Conference on Neural Networks for Ocean Engineering, pp. 91-98, Aug. 1991.
Malkoff et al., "A Neural Network Approach To The Detection Problem Using Joint Time-Frequency Distributions"; ICASSP '90, pp. 2739-2742, vol. 5 Apr. 1990.
Dranger et al., "Adaptive Classifiers Using Ontogenetic Neural Networks With Feedback"; 1993 IEEE International Symposium on Circuits and Systems, pp. 2156-2159, vol. 4 May 1993.
Hollis et al, "A Neural Network Learning Algorithm, Tailored for VLSI Implementation", IEEE Transactions on Neural Networks, Sep. 1994.
Oh et al, "Query Based Learning in a Multilayered Perception in the Presence of Data Filter", Proceeding of the 1st Intern. Forum on Application of Neural Networks to Power Systems, IEEE Jul. 1991.
Babri et al., "Deep Feedforward Networks: Application to Pattern Recognition", IEEE ICNN, Jun. 1996.
Ji et al, "Experimental Study of Direct, Adaptive SPSA Control System with Diagonal Recurrent Neural Network Controller", IEEE Proceedings of the Southeastern '96. Bringing Together Education; Science and Technology, Apr. 1996.
Hewett et al, "Teaching Students to Model Neural Circuits and Neural Networks Using an Electronic Spreadsheet Simulator", Behavior Research Methods, Instruments & Computers, vol. 17, No. 2, pp. 339-344, Apr. 1985.
Caudill, M., "Neural Nets Smarts to Spreadsheets Slowly", BYTE, vol. 18, No. 1, pp. 221-222, Jan. 1993.
Lead et al, "A Hybrid Connectionist Expert System to Solve Classification Problems" IEEE Proceedings of Computer in Cardiology, Sep. 1993.
Ekong et al, "Fault Tolerant Neural Networks For Control Systems"; IEEE Conference on Communications, Computers & Power in the Modern Environment, pp. 269-275, May 1993.
Saga et al, "Self-Supervised Learning Model"; Fujitsu Scientific & Technical Journal, 29, 3, pp. 209-216, Sep. 1993.
Tuazon et al, "A New Digital Neural Network And Its Application"; 1993 Canadian Conference on Electrical & Computer Engineering, p. 481-485, vol. 1, Sep. 14-17, 1993.
Antonini, "Spreadsheet Simulation Of Artificial Neural Networks"; IJCNN-91-Seattle, p. 910, vol. 2.
Freedman et al, "Expert Systems In Spreadsheets: Modeling The Wall Street User Domain"; The First Int'l Conference on AI on Wall Street, pp. 296-301.
Walter et al, "A Spreadsheet Method For Studying Neural Networks", Proceedings of the 1990 Symposium on Applied Computing, pp. 42-44.
Davis George
Hafiz Tariq R.
LandOfFree
Neural network-based target seeking system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neural network-based target seeking system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network-based target seeking system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2222743