Abstract: The energy efficiency of deep neural network (DNN) inference can be improved with custom accelerators. DNN inference accelerators often employ specialized hardware techniques to improve ...
Abstract: Recently, researchers have demonstrated multiple-bits-per-cell (MBPC) data storage using resistive random access memory (RRAM) device technologies. In MBPC storage, a level allocation ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results