Handling sequences with a competitive recurrent network

The competitive recurrent network, a network with competitive layers that is able to handle sequences of input patterns, is presented. The mechanism enabling the network to handle sequential aspects is a feedback loop. A modified form of Hebbian learning is employed together with several types of forgetting. The updating mechanisms used have been developed specifically for the network architecture. It is shown for both forecasting and classification tasks how various types of sequences can be handled by this network