A new recurrent neural network is presented, based on the snap-drift algorithm. The simple recurrent network (SRN) architecture is adopted, with the hidden layer values copied back to the input layer. A form of reinforcement learning is deployed in which the mode is swapped between the snap and drift unsupervised modes when performance drops, and in which adaptation is probabilistic, whereby the probability of a neuron being adapted is reduced as performance increases. The algorithm is evaluated for the problem of phrase recognition on a set of phrases from the Lancaster Parsed Corpus, and it is found to exhibit effective learning that is faster than alternative neural network methods.
展开▼
