Genetically adaptive neural network classification systems and methods
View Patent ↗Genetically adaptive neural network systems and methods provide environmentally adaptable classification algorithms for use, among other things, in multi-static active sonar classification. Classification training occurs in-situ with data acquired at the onset of data collection to improve the classification of sonar energy detections in difficult littoral environments. Accordingly, in-situ training sets are developed while the training process is supervised and refined. Candidate weights vectors evolve through genetic-based search procedures, and the fitness of candidate weight vectors is evaluated. Feature vectors of interest may be classified using multiple neural networks and statistical averaging techniques to provide accurate and reliable signal classification.
1. A system for genetically adaptive signal classification comprising:
a learning supervisor for processing a population of weight vectors in a neural network using training data which includes a plurality of previously classified sonar waveforms;
a fitness evaluator coupled to the learning supervisor for evaluating a fitness of the weight vectors against a stopping criterion based on the processed weight vectors; and
a genetic operator, coupled to the fitness evaluator and the learning supervisor, for modifying the population of weight vectors and providing the modified weight vectors to the learning supervisor until the fitness evaluator indicates that the fitness of the weight vectors meets the stopping criterion, thereby yielding an acceptable set of weight vectors;
wherein the neural network subsequently uses the acceptable set of weight vectors to classify sonar waveforms into a plurality of data classes.
2. The system of claim 1 , wherein the learning supervisor has an input port to receive an initial set of random weight vectors.
3. The system of claim 1 , wherein the genetic operator includes a selection operator for selecting weight vectors proportional to their fitness and for discarding weight vectors not meeting a specified level of fitness.
4. The system of claim 3 , wherein the genetic operator further includes a reproduction operator for duplicating the selected weight vectors to produce a population with the same number of weight vectors prior to selection by the selection operator.
5. The system of claim 4 , wherein the genetic operator further includes a crossover operator for exchanging weight vector information around a crossover point.
6. The system of claim 5 , wherein the crossover operator randomly selects a variable number of weight vector pairs from a current population before exchanging weight vector information around the crossover point.
7. The system of claim 6 , wherein the genetic operator includes a mutation operator for randomly changing weight vectors.
8. The system of claim 1 , wherein classifying the sonar waveforms into a plurality of data classes comprises classifying a sonar waveform into a target data class to detect a target.
9. A method for genetically adaptive signal classification comprising:
processing a population of weight vectors in a neural network using training data which includes a plurality of previously classified sonar waveforms;
evaluating a fitness of the weight vectors against a stopping criterion based on the processed weight vectors; and
modifying the population of weight vectors and evaluating the fitness of the modified weight vectors until the fitness of the modified weight vectors meets the stopping criterion thereby yielding an acceptable set of weight vectors; and
subsequently using the acceptable set of weight vectors by the neural network to classify sonar waveforms into a plurality of classes.
10. The method of claim 9 , wherein processing the population of weight vectors includes receiving an initial set of random weight vectors.
11. The method of claim 9 , wherein genetically modifying the population of weight vectors includes selecting weight vectors proportional to their fitness and discarding weight vectors not meeting a specified level of fitness.
12. The method of claim 11 , wherein genetically modifying the population of weight vectors further includes duplicating the selected weight vectors to produce a population with the same number of weight vectors as the initial population.
13. The method of claim 12 , wherein genetically modifying the population of weight vectors includes exchanging weight vector information around a crossover point.
14. The method of claim 13 , wherein exchanging weight vector information includes randomly selecting a variable number of weight vector pairs from the current population before exchanging weight vector information around the crossover point.
15. The method of claim 14 , wherein genetically modifying the population of weight vectors includes randomly changing weight vectors.
16. The method of claim 9 , wherein classifying the sonar waveforms into a plurality of data classes comprises classifying a sonar waveform into a target data class to detect a target.
17. A system for genetically adaptive signal classification of sonar waveforms comprising:
a learning supervisor for processing a population of weight vectors in a neural network using training data which includes a plurality of previously classified sonar waveforms;
a fitness evaluator coupled to the learning supervisor for evaluating a fitness of the weight vectors against a stopping criterion based on the processed weight vectors; and
a genetic operator, coupled to the fitness evaluator and the learning supervisor, for modifying the population of weight vectors and providing the modified weight vectors to the learning supervisor until the fitness evaluator indicates that the fitness of the weight vectors meets the stopping criterion, thereby yielding an acceptable set of weight vectors,
wherein the neural network subsequently uses the acceptable set of weight vectors to classify sonar waveforms into a plurality of classes.
18. The system of claim 17 , wherein the learning supervisor has an input port to receive an initial set of random weight vectors.
19. The system of claim 17 , wherein the genetic operator includes a selection operator for selecting weight vectors proportional to their fitness and for discarding weight vectors not meeting a specified level of fitness.
20. The system of claim 19 , wherein the genetic operator further includes a reproduction operator for duplicating the selected weight vectors to produce a population with the same number of weight vectors prior to selection by the selection operator.
21. The system of claim 20 , wherein the genetic operator further includes a crossover operator for exchanging weight vector information around a crossover point.
22. The system of claim 21 , wherein the crossover operator randomly selects a variable number of weight vector pairs from a current population before exchanging weight vector information around the crossover point.
23. The system of claim 22 , wherein the genetic operator includes a mutation operator for randomly changing weight vectors.
24. The system of claim 23 , wherein the neural network uses a subset of the fittest weight vectors to classify the mission data.
25. The system of claim 17 , wherein classifying the sonar waveforms into a plurality of data classes comprises classifying a sonar waveform into a target data class to detect a target.
26. A system for genetically adaptive signal classification comprising:
a learning supervisor for processing a population of weight vectors in a neural network using training data which includes one of sonar signals, voice signals, and image signals;
a fitness evaluator coupled to the learning supervisor for evaluating a fitness of the weight vectors against a stopping criterion based on the processed weight vectors; and
a genetic operator, coupled to the fitness evaluator and the learning supervisor, for modifying the population of weight vectors and providing the modified weight vectors to the learning supervisor until the fitness evaluator indicates that the fitness of the weight vectors meets the stopping criterion, thereby yielding an acceptable set of weight vectors;
wherein the neural network subsequently uses the acceptable set of weight vectors to classify the one of sonar signals, voice signals, and image signals into a plurality of data classes.