TY - CONF AU - Neftci, Emre AU - Yu, Zhenming AU - Leroux, Nathan TI - Training-to-Learn with Memristive Devices M1 - FZJ-2024-02778 PY - 2023 AB - 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. T2 - Neuromorphic Materials, Devices, Circuits and Systems CY - 23 Jan 2023 - 25 Jan 2023, València (Spain) Y2 - 23 Jan 2023 - 25 Jan 2023 M2 - València, Spain LB - PUB:(DE-HGF)6 DO - DOI:10.29363/nanoge.neumatdecas.2023.013 UR - https://juser.fz-juelich.de/record/1025210 ER -