A new technical paper titled “Optimization of Projected Phase Change Memory for Analog In-Memory Computing Inference” was published by researchers at IBM Research.
“A systematic study of the electrical properties-including resistance values, memory window, resistance drift, read noise, and their impact on the accuracy of large neural networks of various types and with tens of millions of weights is performed. It is shown that the DNN accuracy can be improved by the PCM with liner for both the short term and long term after programming, due to reduced resistance drift and read noise, respectively, despite the trade-off of reduced memory window,” states the paper.
Find the technical paper here. Published April 2023.
Li, Ning, Charles Mackin, An Chen, Kevin Brew, Timothy Philip, Andrew Simon, Iqbal Saraf et al. “Optimization of Projected Phase Change Memory for Analog In‐Memory Computing Inference.” Advanced Electronic Materials (2022): 2201190.
Leave a Reply