Guardado en:
Detalles Bibliográficos
Autores principales: Sakemi, Yusuke, Okamoto, Yuji, Morie, Takashi, Nobukawa, Sou, Hosomi, Takeo, Aihara, Kazuyuki
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2412.09010
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908276451442688
author Sakemi, Yusuke
Okamoto, Yuji
Morie, Takashi
Nobukawa, Sou
Hosomi, Takeo
Aihara, Kazuyuki
author_facet Sakemi, Yusuke
Okamoto, Yuji
Morie, Takashi
Nobukawa, Sou
Hosomi, Takeo
Aihara, Kazuyuki
contents Large-scale deep learning models are increasingly constrained by their immense energy consumption, limiting their scalability and applicability for edge intelligence. In-memory computing (IMC) offers a promising solution by addressing the von Neumann bottleneck inherent in traditional deep learning accelerators, significantly reducing energy consumption. However, the analog nature of IMC introduces hardware nonidealities that degrade model performance and reliability. This paper presents a novel approach to directly train physical models of IMC, formulated as ordinary-differential-equation (ODE)-based physical neural networks (PNNs). To enable the training of large-scale networks, we propose a technique called differentiable spike-time discretization (DSTD), which reduces the computational cost of ODE-based PNNs by up to 20 times in speed and 100 times in memory. We demonstrate that such large-scale networks enhance the learning performance by exploiting hardware nonidealities on the CIFAR-10 dataset. The proposed bottom-up methodology is validated through the post-layout SPICE simulations on the IMC circuit with nonideal characteristics using the sky130 process. The proposed PNN approach reduces the discrepancy between the model behavior and circuit dynamics by at least an order of magnitude. This work paves the way for leveraging nonideal physical devices, such as non-volatile resistive memories, for energy-efficient deep learning applications.
format Preprint
id arxiv_https___arxiv_org_abs_2412_09010
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Harnessing Nonidealities in Analog In-Memory Computing Circuits: A Physical Modeling Approach for Neuromorphic Systems
Sakemi, Yusuke
Okamoto, Yuji
Morie, Takashi
Nobukawa, Sou
Hosomi, Takeo
Aihara, Kazuyuki
Machine Learning
Large-scale deep learning models are increasingly constrained by their immense energy consumption, limiting their scalability and applicability for edge intelligence. In-memory computing (IMC) offers a promising solution by addressing the von Neumann bottleneck inherent in traditional deep learning accelerators, significantly reducing energy consumption. However, the analog nature of IMC introduces hardware nonidealities that degrade model performance and reliability. This paper presents a novel approach to directly train physical models of IMC, formulated as ordinary-differential-equation (ODE)-based physical neural networks (PNNs). To enable the training of large-scale networks, we propose a technique called differentiable spike-time discretization (DSTD), which reduces the computational cost of ODE-based PNNs by up to 20 times in speed and 100 times in memory. We demonstrate that such large-scale networks enhance the learning performance by exploiting hardware nonidealities on the CIFAR-10 dataset. The proposed bottom-up methodology is validated through the post-layout SPICE simulations on the IMC circuit with nonideal characteristics using the sky130 process. The proposed PNN approach reduces the discrepancy between the model behavior and circuit dynamics by at least an order of magnitude. This work paves the way for leveraging nonideal physical devices, such as non-volatile resistive memories, for energy-efficient deep learning applications.
title Harnessing Nonidealities in Analog In-Memory Computing Circuits: A Physical Modeling Approach for Neuromorphic Systems
topic Machine Learning
url https://arxiv.org/abs/2412.09010