System and method for determining node functionality in artifici

Details System and method for determining node functionality in artifici System and method for determining node functionality in artifici

1996-08-23

1998-07-28

Davis, George B.

Data processing: artificial intelligence

Neural network

Learning method

706 16, 706 20, 706 27, G06F 1518

Patent

active

057874085

ABSTRACT:
A system for unwrapping an artificial neural network (ANN) to determine the tilization and functionality of the nodes uses a network generator for generating an initial ANN architecture. Training and pruning processors operate to generate minimal ANN architectures having increasingly lower levels of classification accuracy. A network analyzer uses an analysis controller to receive minimal ANN architectures from the pruning processor. A connection analyzer operates on the minimal ANN architectures to identify the inputs to the minimal ANN architecture and determine the information represented by and contained in the network inputs. A node analyzer, coupled to the connection analyzer, then defines the utilization and functionality of each node in the minimal ANN architecture in terms of known functions.

REFERENCES:
patent: 5438644 (1995-08-01), Fu
patent: 5487117 (1996-01-01), Burges et al.
patent: 5590218 (1996-12-01), Ornstein
patent: 5619616 (1997-04-01), Brady et al.
patent: 5636326 (1997-06-01), Stork et al.
patent: 5640492 (1997-06-01), Cortes et al.
patent: 5640494 (1997-06-01), Jabri et al.
patent: 5659666 (1997-08-01), Thaler

Affiliated with

Also associated with

Rating

System and method for determining node functionality in artifici 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 determining node functionality in artifici, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for determining node functionality in artifici will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-34552