STORAGE OF WORDS IN A NEURAL-NETWORK

We present a neural network that may be used to store patterns with an especific correlation. It is based on a one-shot learning rule that i ncludes multi-neuron synapses. Dilution of connections is introduced n aturally, simplifying the implementation. The model may be related to the human ability to store and retrieve words. Numerical simulations o n a small network give an insight into the properties of this type of network.