Storing deep neural network weights in non-volatile storage systems using vertical error correction codes

Abstract

Techniques are presented for efficiently storing deep neural network (DNN) weights or similar type data sets in non-volatile memory. For data sets, such as DNN weights, where the elements are multi-bit values, bits of the same level of significance from the elements of the data set are formed into data streams. For example, the most significant bit from each of the data elements are formed into one data stream, the next most significant bit into a second data stream, and so on. The different bit streams are then encoded with differing strengths of error correction code (ECC), with streams corresponding to more significant bits encoded with stronger ECC code than streams corresponding to less significant bits, giving the more significant bits of the data set elements a higher level of protection.