Hardware Implementation of New Analog Memory for Neural Networks

Koji NAKAJIMA; Shigeo SATO; Tomoyasu KITAURA; Junichi MUROTA; Yasuji SAWADA

Hardware Implementation of New Analog Memory for Neural Networks

Koji NAKAJIMA, Shigeo SATO, Tomoyasu KITAURA, Junichi MUROTA, Yasuji SAWADA

Full Text Views

0

Share
Cite this

Summary :

We have fabricated a new analog memory with a floating gate as a key component to store synaptic weights for integrated artificial neural networks. The new analog memory comprises a tunnel junction (poly-Si/poly-si oxide/poly-Si sandwich structure), a thin-film transistor, two capacitors, and a floating gate MOSFET. The diffusion of the charges injected through the tunnel junction is controlled by switching operation of the thin-film transistor, and we refer to the new analog memory as switched diffusion analog memory (SDAM). The obtained characteristics of SDAM are a fast switching speed and an improved linearity between the potential of the floating gate and the number of pulse inputs. SDAM can be used in a neural network in which write/erase and read operations are performed simultaneously.

Publication: IEICE TRANSACTIONS on Electronics Vol.E78-C No.1 pp.101-105

Publication Date: 1995/01/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Integrated Electronics

Cite this

Copy

Koji NAKAJIMA, Shigeo SATO, Tomoyasu KITAURA, Junichi MUROTA, Yasuji SAWADA, "Hardware Implementation of New Analog Memory for Neural Networks" in IEICE TRANSACTIONS on Electronics, vol. E78-C, no. 1, pp. 101-105, January 1995, doi: .
Abstract: We have fabricated a new analog memory with a floating gate as a key component to store synaptic weights for integrated artificial neural networks. The new analog memory comprises a tunnel junction (poly-Si/poly-si oxide/poly-Si sandwich structure), a thin-film transistor, two capacitors, and a floating gate MOSFET. The diffusion of the charges injected through the tunnel junction is controlled by switching operation of the thin-film transistor, and we refer to the new analog memory as switched diffusion analog memory (SDAM). The obtained characteristics of SDAM are a fast switching speed and an improved linearity between the potential of the floating gate and the number of pulse inputs. SDAM can be used in a neural network in which write/erase and read operations are performed simultaneously.
URL: https://globals.ieice.org/en_transactions/electronics/10.1587/e78-c_1_101/_p

Copy

@ARTICLE{e78-c_1_101,
author={Koji NAKAJIMA, Shigeo SATO, Tomoyasu KITAURA, Junichi MUROTA, Yasuji SAWADA, },
journal={IEICE TRANSACTIONS on Electronics},
title={Hardware Implementation of New Analog Memory for Neural Networks},
year={1995},
volume={E78-C},
number={1},
pages={101-105},
abstract={We have fabricated a new analog memory with a floating gate as a key component to store synaptic weights for integrated artificial neural networks. The new analog memory comprises a tunnel junction (poly-Si/poly-si oxide/poly-Si sandwich structure), a thin-film transistor, two capacitors, and a floating gate MOSFET. The diffusion of the charges injected through the tunnel junction is controlled by switching operation of the thin-film transistor, and we refer to the new analog memory as switched diffusion analog memory (SDAM). The obtained characteristics of SDAM are a fast switching speed and an improved linearity between the potential of the floating gate and the number of pulse inputs. SDAM can be used in a neural network in which write/erase and read operations are performed simultaneously.},
keywords={},
doi={},
ISSN={},
month={January},}

Copy

TY - JOUR
TI - Hardware Implementation of New Analog Memory for Neural Networks
T2 - IEICE TRANSACTIONS on Electronics
SP - 101
EP - 105
AU - Koji NAKAJIMA
AU - Shigeo SATO
AU - Tomoyasu KITAURA
AU - Junichi MUROTA
AU - Yasuji SAWADA
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Electronics
SN -
VL - E78-C
IS - 1
JA - IEICE TRANSACTIONS on Electronics
Y1 - January 1995
AB - We have fabricated a new analog memory with a floating gate as a key component to store synaptic weights for integrated artificial neural networks. The new analog memory comprises a tunnel junction (poly-Si/poly-si oxide/poly-Si sandwich structure), a thin-film transistor, two capacitors, and a floating gate MOSFET. The diffusion of the charges injected through the tunnel junction is controlled by switching operation of the thin-film transistor, and we refer to the new analog memory as switched diffusion analog memory (SDAM). The obtained characteristics of SDAM are a fast switching speed and an improved linearity between the potential of the floating gate and the number of pulse inputs. SDAM can be used in a neural network in which write/erase and read operations are performed simultaneously.
ER -