Data processing: artificial intelligence – Neural network – Structure
Reexamination Certificate
2008-01-29
2008-01-29
Vincent, David (Department: 2129)
Data processing: artificial intelligence
Neural network
Structure
C706S012000, C706S014000, C706S015000, C706S016000
Reexamination Certificate
active
10483093
ABSTRACT:
This invention relates to an information processing device and method that enable generation of an unlearned new pattern. Data xtcorresponding to a predetermined time series pattern is inputted to an input layer (11) of a recurrent neural network (1), and a prediction value x*t+1is acquired from an output layer13. A difference between teacher data xt+1and the prediction value x*t+1is learned by a back propagation method, and a weighting coefficient of an intermediate layer12is set at a predetermined value. After the recurrent neural network is caused to learn plural time series patterns, a parameter having a different value from the value in learning is inputted to parametric bias nodes (11-2), and an unlearned time series pattern corresponding to the parameter is generated from the output layer (13). This invention can be applied to a robot.
REFERENCES:
patent: 5408424 (1995-04-01), Lo
patent: 5956702 (1999-09-01), Matsuoka et al.
patent: 6249781 (2001-06-01), Sutton
patent: 6728691 (2004-04-01), Neuneier et al.
patent: 6735580 (2004-05-01), Li et al.
patent: 2002-86378 (2002-03-01), None
Takase, H. et al., “Time Sequential Pattern Transformation and Attractors of Recurrent Neural Networks”, In: Proc. of 1993 International Joint Conference on Neural Networks, 1993, pp. 2319-2321.
Ito Masato
Tani Jun
Fernández Rivas Omar F
Frommer William S.
Frommer & Lawrence & Haug LLP
Presson Thomas F.
Riken
LandOfFree
Information processing apparatus and method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Information processing apparatus and method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Information processing apparatus and method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3914907