Building a Hierarchy with Neural Networks: An example - Image Vector Quantization
01 January 1987
Electronic Neural Networks can perform the function of associative memory. The networks search through a list of stored memories and attempt to find the best match of a key to one of the memories.
Thus the network does a combination of content-addressable search and error correction. The number of random memories that a network can store is limited to a fraction of the number of electronic neurons in the circuit.