001038036 001__ 1038036
001038036 005__ 20250203103305.0
001038036 0247_ $$2doi$$a10.48550/ARXIV.2403.06712
001038036 0247_ $$2doi$$a10.48550/arXiv.2403.06712
001038036 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-01085
001038036 037__ $$aFZJ-2025-01085
001038036 1001_ $$0P:(DE-Juel1)190500$$aYu, Zhenming$$b0$$ufzj
001038036 245__ $$aThe Ouroboros of Memristors: Neural Networks Facilitating Memristor Programming
001038036 260__ $$barXiv$$c2024
001038036 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1738239409_31383
001038036 3367_ $$2ORCID$$aWORKING_PAPER
001038036 3367_ $$028$$2EndNote$$aElectronic Article
001038036 3367_ $$2DRIVER$$apreprint
001038036 3367_ $$2BibTeX$$aARTICLE
001038036 3367_ $$2DataCite$$aOutput Types/Working Paper
001038036 520__ $$aMemristive devices hold promise to improve the scale and efficiency of machine learning and neuromorphic hardware, thanks to their compact size, low power consumption, and the ability to perform matrix multiplications in constant time. However, on-chip training with memristor arrays still faces challenges, including device-to-device and cycle-to-cycle variations, switching non-linearity, and especially SET and RESET asymmetry. To combat device non-linearity and asymmetry, we propose to program memristors by harnessing neural networks that map desired conductance updates to the required pulse times. With our method, approximately 95% of devices can be programmed within a relative percentage difference of +-50% from the target conductance after just one attempt. Our approach substantially reduces memristor programming delays compared to traditional write-and-verify methods, presenting an advantageous solution for on-chip training scenarios. Furthermore, our proposed neural network can be accelerated by memristor arrays upon deployment, providing assistance while reducing hardware overhead compared with previous works. This work contributes significantly to the practical application of memristors, particularly in reducing delays in memristor programming. It also envisions the future development of memristor-based machine learning accelerators.
001038036 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001038036 536__ $$0G:(BMBF)16ME0400$$aBMBF 16ME0400 - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (16ME0400)$$c16ME0400$$x1
001038036 536__ $$0G:(BMBF)03ZU1106CA$$aBMBF 03ZU1106CA - NeuroSys: Algorithm-Hardware Co-Design (Projekt C) - A (03ZU1106CA)$$c03ZU1106CA$$x2
001038036 536__ $$0G:(DE-Juel1)BMBF-03ZU1106CB$$aBMBF 03ZU1106CB - NeuroSys: Algorithm-Hardware Co-Design (Projekt C) - B (BMBF-03ZU1106CB)$$cBMBF-03ZU1106CB$$x3
001038036 588__ $$aDataset connected to DataCite
001038036 650_7 $$2Other$$aEmerging Technologies (cs.ET)
001038036 650_7 $$2Other$$aFOS: Computer and information sciences
001038036 7001_ $$0P:(DE-Juel1)192385$$aYang, Ming-Jay$$b1$$ufzj
001038036 7001_ $$0P:(DE-Juel1)190112$$aFinkbeiner, Jan$$b2$$ufzj
001038036 7001_ $$0P:(DE-Juel1)174486$$aSiegel, Sebastian$$b3$$ufzj
001038036 7001_ $$0P:(DE-Juel1)188145$$aStrachan, John Paul$$b4$$ufzj
001038036 7001_ $$0P:(DE-Juel1)188273$$aNeftci, Emre$$b5$$eCorresponding author
001038036 773__ $$a10.48550/arXiv.2403.06712
001038036 8564_ $$uhttps://arxiv.org/abs/2403.06712
001038036 8564_ $$uhttps://juser.fz-juelich.de/record/1038036/files/2403.06712v1.pdf$$yOpenAccess
001038036 909CO $$ooai:juser.fz-juelich.de:1038036$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001038036 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)190500$$aForschungszentrum Jülich$$b0$$kFZJ
001038036 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)192385$$aForschungszentrum Jülich$$b1$$kFZJ
001038036 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)190112$$aForschungszentrum Jülich$$b2$$kFZJ
001038036 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)174486$$aForschungszentrum Jülich$$b3$$kFZJ
001038036 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188145$$aForschungszentrum Jülich$$b4$$kFZJ
001038036 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188273$$aForschungszentrum Jülich$$b5$$kFZJ
001038036 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5234$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
001038036 9141_ $$y2024
001038036 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001038036 920__ $$lyes
001038036 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x0
001038036 9201_ $$0I:(DE-Juel1)PGI-14-20210412$$kPGI-14$$lNeuromorphic Compute Nodes$$x1
001038036 980__ $$apreprint
001038036 980__ $$aVDB
001038036 980__ $$aUNRESTRICTED
001038036 980__ $$aI:(DE-Juel1)PGI-15-20210701
001038036 980__ $$aI:(DE-Juel1)PGI-14-20210412
001038036 9801_ $$aFullTexts