% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Neftci:1025209,
author = {Neftci, Emre},
title = {{P}re-training and {M}eta-learning for {M}emristor
{C}rossbar {A}rrays},
reportid = {FZJ-2024-02777},
year = {2023},
abstract = {Memristive crossbar arrays show promise as non-von Neumann
computing technologies, bringing sophisticated neural
network processing to the edge and facilitating real-world
online learning. However, their deployment for real-world
learning problems faces challenges such as non-linearities
in conductance updates, variations during operation,
fabrication mismatch, conductance drift, and the realities
of gradient descent training.This talk will present methods
to pre-train neural networks to be largely insensitive to
these non-idealities during learning tasks. These methods
rely on a phenomenological model of the device, obtainable
experimentally, and bi-level optimization. We showcase this
effect through meta-learning and a differentiable model of
conductance updates on few-shot learning tasks. Since
pre-training is a necessary procedure for any online
learning scenario at the edge, our results may pave the way
for real-world applications of memristive devices without
significant adaptation overhead.Furthermore, by considering
the programming of memristive devices as a learning problem
in its own right, we demonstrate that the developed methods
can accelerate existing write-verify techniques.},
month = {Feb},
date = {2024-02-21},
organization = {Neuronics Conference, València
(Spain), 21 Feb 2024 - 23 Feb 2024},
subtyp = {Invited},
cin = {PGI-15},
cid = {I:(DE-Juel1)PGI-15-20210701},
pnm = {5234 - Emerging NC Architectures (POF4-523)},
pid = {G:(DE-HGF)POF4-5234},
typ = {PUB:(DE-HGF)6},
doi = {10.29363/nanoge.neuronics.2024.027},
url = {https://juser.fz-juelich.de/record/1025209},
}