001024702 001__ 1024702
001024702 005__ 20250203103144.0
001024702 0247_ $$2doi$$a10.29363/nanoge.neuronics.2024.010
001024702 037__ $$aFZJ-2024-02369
001024702 1001_ $$0P:(DE-Juel1)190500$$aYu, Zhenming$$b0$$eCorresponding author
001024702 1112_ $$aNeuronics Conference$$cValència$$d2024-02-21 - 2024-02-23$$wSpain
001024702 245__ $$aThe Ouroboros of Memristors: Neural Networks Facilitating Memristor Programming
001024702 260__ $$bFUNDACIO DE LA COMUNITAT VALENCIANA SCITO València$$c2023
001024702 29510 $$aProceedings of the Neuronics Conference - FUNDACIO DE LA COMUNITAT VALENCIANA SCITO València, 2023. - ISBN - doi:10.29363/nanoge.neuronics.2024.010
001024702 300__ $$a10
001024702 3367_ $$2ORCID$$aCONFERENCE_PAPER
001024702 3367_ $$033$$2EndNote$$aConference Paper
001024702 3367_ $$2BibTeX$$aINPROCEEDINGS
001024702 3367_ $$2DRIVER$$aconferenceObject
001024702 3367_ $$2DataCite$$aOutput Types/Conference Paper
001024702 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1712643849_1886
001024702 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
001024702 520__ $$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 [1], [2].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. Moreover, our neural pulse predictor demonstrates a significant reduction in memristor programming delay compared to traditional write-and-verify methods, particularly advantageous in applications such as on-chip training and fine-tuning.Upon deployment, the neural pulse predictor can be integrated into memristor accelerators, predicting pulses with an O(1) time complexity while utilizing a minimal fraction of the available memristor arrays, reducing hardware overhead compared with previous works [3]-[6]. Additionally, multiple networks can be trained to operate in parallel and enhance precision across various conductance ranges.Our work contributes significantly to the practical application of memristors, particularly in reducing delays in memristor programming. This work also offers a fresh perspective on the symbiotic relationship between memristors and neural networks and sets the stage for innovation in memristor optimizations.
001024702 536__ $$0G:(DE-HGF)POF4-5233$$a5233 - Memristive Materials and Devices (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001024702 588__ $$aDataset connected to CrossRef Conference
001024702 7001_ $$0P:(DE-Juel1)192385$$aYang, Ming-Jay$$b1$$ufzj
001024702 7001_ $$0P:(DE-Juel1)190112$$aFinkbeiner, Jan$$b2$$ufzj
001024702 7001_ $$0P:(DE-Juel1)174486$$aSiegel, Sebastian$$b3$$ufzj
001024702 7001_ $$0P:(DE-Juel1)188145$$aStrachan, John Paul$$b4$$ufzj
001024702 7001_ $$0P:(DE-Juel1)188273$$aNeftci, Emre$$b5$$ufzj
001024702 773__ $$a10.29363/nanoge.neuronics.2024.010
001024702 909CO $$ooai:juser.fz-juelich.de:1024702$$pVDB
001024702 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)190500$$aForschungszentrum Jülich$$b0$$kFZJ
001024702 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)192385$$aForschungszentrum Jülich$$b1$$kFZJ
001024702 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)190112$$aForschungszentrum Jülich$$b2$$kFZJ
001024702 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)174486$$aForschungszentrum Jülich$$b3$$kFZJ
001024702 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188145$$aForschungszentrum Jülich$$b4$$kFZJ
001024702 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188273$$aForschungszentrum Jülich$$b5$$kFZJ
001024702 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5233$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
001024702 9141_ $$y2024
001024702 920__ $$lyes
001024702 9201_ $$0I:(DE-Juel1)PGI-14-20210412$$kPGI-14$$lNeuromorphic Compute Nodes$$x0
001024702 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x1
001024702 980__ $$acontrib
001024702 980__ $$aVDB
001024702 980__ $$acontb
001024702 980__ $$aI:(DE-Juel1)PGI-14-20210412
001024702 980__ $$aI:(DE-Juel1)PGI-15-20210701
001024702 980__ $$aUNRESTRICTED