MEMORIZING BINARY VECTOR SEQUENCES BY A SPARSELY ENCODED NETWORK

We present a neural network employing Hebbian storage and sparse inter nal coding, which is capable of memorizing and correcting sequences of binary vectors by association. A ternary version of the Kanerva memor y, folded into a feedback configuration, is shown to perform the basic sequence memorization and regeneration function. The inclusion of lat eral connections between the internal cells increases the network capa city considerably and facilitates the correction of individual input p atterns and the detection of large errors. The introduction of higher delays in the transmission lines between the external input-output lay er and the internal memory layer is shown to further improve the netwo rk's error correction capability.