A training algorithm for SpikeProp improving stability of learning process.
Toshiki WakamatsuHaruhiko TakaseHiroharu KawanakaShinji TsuruokaPublished in: IJCNN (2011)
Keyphrases
- training algorithm
- learning process
- back propagation
- neural network
- learning algorithm
- training process
- conjugate gradient
- neural network training
- learning rate
- gradient vector
- support vector machine
- learning experience
- rbf neural network
- learning environment
- reinforcement learning
- training data
- e learning
- active learning
- levenberg marquardt
- machine learning
- data sets