guest ::
| Home > Publications database > Training-to-Learn with Memristive Devices > print |
| 001 | 1025210 | ||
| 005 | 20250203103227.0 | ||
| 024 | 7 | _ | |a 10.29363/nanoge.neumatdecas.2023.013 |2 doi |
| 037 | _ | _ | |a FZJ-2024-02778 |
| 100 | 1 | _ | |a Neftci, Emre |0 P:(DE-Juel1)188273 |b 0 |u fzj |
| 111 | 2 | _ | |a Neuromorphic Materials, Devices, Circuits and Systems |c València |d 2023-01-23 - 2023-01-25 |w Spain |
| 245 | _ | _ | |a Training-to-Learn with Memristive Devices |
| 260 | _ | _ | |c 2023 |
| 336 | 7 | _ | |a Conference Paper |0 33 |2 EndNote |
| 336 | 7 | _ | |a Other |2 DataCite |
| 336 | 7 | _ | |a INPROCEEDINGS |2 BibTeX |
| 336 | 7 | _ | |a conferenceObject |2 DRIVER |
| 336 | 7 | _ | |a LECTURE_SPEECH |2 ORCID |
| 336 | 7 | _ | |a Conference Presentation |b conf |m conf |0 PUB:(DE-HGF)6 |s 1714574803_3667 |2 PUB:(DE-HGF) |x Invited |
| 520 | _ | _ | |a Memristive crossbar arrays are promising non-von Neumann computing technologies to enable real-world, onlinelearning in neural networks. However, their deployment to real-world learning problems is hindered by their non-linearitiesin conductance updates, variation during operation, fabrication mismatch and the realities of gradient descent training. In thiswork, we show that, with a phenomenological model of the device and bi-level optimization, it is possible to pre-train the neuralnetwork to be largely insensitive to such non-idealities on learning tasks. We demonstrate this effect using Model Agnostic Meta Learning (MAML) and a differentiable model of the conductance update on the Omniglot few-shot learning task. Since pre-training is a necessary procedure for any on-line learning scenario at the edge, our results may pave the way towards real-world applications of memristive devices without significant adaption overhead. |
| 536 | _ | _ | |a 5234 - Emerging NC Architectures (POF4-523) |0 G:(DE-HGF)POF4-5234 |c POF4-523 |f POF IV |x 0 |
| 588 | _ | _ | |a Dataset connected to CrossRef Conference |
| 700 | 1 | _ | |a Yu, Zhenming |0 P:(DE-Juel1)190500 |b 1 |u fzj |
| 700 | 1 | _ | |a Leroux, Nathan |0 P:(DE-Juel1)194421 |b 2 |
| 773 | _ | _ | |a 10.29363/nanoge.neumatdecas.2023.013 |
| 856 | 4 | _ | |u https://www.nanoge.org/proceedings/NeuMatDeCaS/636e689d63c3311959c7c0fa |
| 909 | C | O | |o oai:juser.fz-juelich.de:1025210 |p VDB |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 0 |6 P:(DE-Juel1)188273 |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 1 |6 P:(DE-Juel1)190500 |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 2 |6 P:(DE-Juel1)194421 |
| 913 | 1 | _ | |a DE-HGF |b Key Technologies |l Natural, Artificial and Cognitive Information Processing |1 G:(DE-HGF)POF4-520 |0 G:(DE-HGF)POF4-523 |3 G:(DE-HGF)POF4 |2 G:(DE-HGF)POF4-500 |4 G:(DE-HGF)POF |v Neuromorphic Computing and Network Dynamics |9 G:(DE-HGF)POF4-5234 |x 0 |
| 914 | 1 | _ | |y 2024 |
| 920 | 1 | _ | |0 I:(DE-Juel1)PGI-15-20210701 |k PGI-15 |l Neuromorphic Software Eco System |x 0 |
| 980 | _ | _ | |a conf |
| 980 | _ | _ | |a VDB |
| 980 | _ | _ | |a I:(DE-Juel1)PGI-15-20210701 |
| 980 | _ | _ | |a UNRESTRICTED |
| Library | Collection | CLSMajor | CLSMinor | Language | Author |
|---|