Low-Power and High-Density Neuron Device for Simultaneous Processing of Excitatory and Inhibitory Signals in Neuromorphic Systems
A positive-feedback (PF) neuron device capable of threshold tuning and simultaneously processing excitatory (G±) and inhibitory (G-) signals is experimentally demonstrated to replace conventional neuron circuits, for the first time. Thanks to the PF operation, the PF neuron device with st...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9249234/ |
| _version_ | 1831558647994384384 |
|---|---|
| author | Sung Yun Woo Dongseok Kwon Nagyong Choi Won-Mook Kang Young-Tak Seo Min-Kyu Park Jong-Ho Bae Byung-Gook Park Jong-Ho Lee |
| author_facet | Sung Yun Woo Dongseok Kwon Nagyong Choi Won-Mook Kang Young-Tak Seo Min-Kyu Park Jong-Ho Bae Byung-Gook Park Jong-Ho Lee |
| author_sort | Sung Yun Woo |
| collection | DOAJ |
| description | A positive-feedback (PF) neuron device capable of threshold tuning and simultaneously processing excitatory (G±) and inhibitory (G-) signals is experimentally demonstrated to replace conventional neuron circuits, for the first time. Thanks to the PF operation, the PF neuron device with steep switching characteristics can implement integrate-and-fire (IF) function of neurons with low-energy consumption. The structure of the PF neuron device efficiently merges a gated PNPN diode and a single MOSFET. Integrateand-fire (IF) operation with steep subthreshold swing (SS <; 1 mV/dec) is experimentally implemented by carriers accumulated in an n floating body of the PF neuron device. The carriers accumulated in the n floating body are discharged by an inhibitory signal applied to the merged FET. Moreover, the threshold voltage (V<sub>th</sub>) of the proposed PF neuron is controlled by using a charge storage layer. The low-energy consuming PF neuron circuit (~0.62 pJ/spike) consists of one PF device and only five MOSFETs for the IF and reset operation. In a high-level system simulation, a deep-spiking neural network (D-SNN) based on PF neurons with four hidden layers (1024 neurons in each layer) shows high-accuracy (98.55%) during a MNIST classification task. The PF neuron device provides a viable solution for high-density and low-energy neuromorphic systems. |
| first_indexed | 2024-12-17T05:13:54Z |
| format | Article |
| id | doaj.art-1470e541c27b4b18ab794fd340bcf8d8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T05:13:54Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1470e541c27b4b18ab794fd340bcf8d82022-12-21T22:02:11ZengIEEEIEEE Access2169-35362020-01-01820263920264710.1109/ACCESS.2020.30360889249234Low-Power and High-Density Neuron Device for Simultaneous Processing of Excitatory and Inhibitory Signals in Neuromorphic SystemsSung Yun Woo0https://orcid.org/0000-0002-0857-3183Dongseok Kwon1https://orcid.org/0000-0001-7676-8938Nagyong Choi2Won-Mook Kang3https://orcid.org/0000-0003-1812-3407Young-Tak Seo4https://orcid.org/0000-0003-3970-4876Min-Kyu Park5Jong-Ho Bae6https://orcid.org/0000-0002-1786-7132Byung-Gook Park7https://orcid.org/0000-0002-2962-2458Jong-Ho Lee8https://orcid.org/0000-0003-3559-9802Department of ECE and ISRC, Seoul National University, Seoul, South KoreaDepartment of ECE and ISRC, Seoul National University, Seoul, South KoreaDepartment of ECE and ISRC, Seoul National University, Seoul, South KoreaDepartment of ECE and ISRC, Seoul National University, Seoul, South KoreaDepartment of ECE and ISRC, Seoul National University, Seoul, South KoreaDepartment of ECE and ISRC, Seoul National University, Seoul, South KoreaDepartment of Electrical Engineering, Kookmin University, Seoul, South KoreaDepartment of ECE and ISRC, Seoul National University, Seoul, South KoreaDepartment of ECE and ISRC, Seoul National University, Seoul, South KoreaA positive-feedback (PF) neuron device capable of threshold tuning and simultaneously processing excitatory (G±) and inhibitory (G-) signals is experimentally demonstrated to replace conventional neuron circuits, for the first time. Thanks to the PF operation, the PF neuron device with steep switching characteristics can implement integrate-and-fire (IF) function of neurons with low-energy consumption. The structure of the PF neuron device efficiently merges a gated PNPN diode and a single MOSFET. Integrateand-fire (IF) operation with steep subthreshold swing (SS <; 1 mV/dec) is experimentally implemented by carriers accumulated in an n floating body of the PF neuron device. The carriers accumulated in the n floating body are discharged by an inhibitory signal applied to the merged FET. Moreover, the threshold voltage (V<sub>th</sub>) of the proposed PF neuron is controlled by using a charge storage layer. The low-energy consuming PF neuron circuit (~0.62 pJ/spike) consists of one PF device and only five MOSFETs for the IF and reset operation. In a high-level system simulation, a deep-spiking neural network (D-SNN) based on PF neurons with four hidden layers (1024 neurons in each layer) shows high-accuracy (98.55%) during a MNIST classification task. The PF neuron device provides a viable solution for high-density and low-energy neuromorphic systems.https://ieeexplore.ieee.org/document/9249234/Neuron devicepositive-feedback (PF) devicehardware-based neural networkssemiconductor device reliabilitysilicon-on-insulator (SOI) technology |
| spellingShingle | Sung Yun Woo Dongseok Kwon Nagyong Choi Won-Mook Kang Young-Tak Seo Min-Kyu Park Jong-Ho Bae Byung-Gook Park Jong-Ho Lee Low-Power and High-Density Neuron Device for Simultaneous Processing of Excitatory and Inhibitory Signals in Neuromorphic Systems IEEE Access Neuron device positive-feedback (PF) device hardware-based neural networks semiconductor device reliability silicon-on-insulator (SOI) technology |
| title | Low-Power and High-Density Neuron Device for Simultaneous Processing of Excitatory and Inhibitory Signals in Neuromorphic Systems |
| title_full | Low-Power and High-Density Neuron Device for Simultaneous Processing of Excitatory and Inhibitory Signals in Neuromorphic Systems |
| title_fullStr | Low-Power and High-Density Neuron Device for Simultaneous Processing of Excitatory and Inhibitory Signals in Neuromorphic Systems |
| title_full_unstemmed | Low-Power and High-Density Neuron Device for Simultaneous Processing of Excitatory and Inhibitory Signals in Neuromorphic Systems |
| title_short | Low-Power and High-Density Neuron Device for Simultaneous Processing of Excitatory and Inhibitory Signals in Neuromorphic Systems |
| title_sort | low power and high density neuron device for simultaneous processing of excitatory and inhibitory signals in neuromorphic systems |
| topic | Neuron device positive-feedback (PF) device hardware-based neural networks semiconductor device reliability silicon-on-insulator (SOI) technology |
| url | https://ieeexplore.ieee.org/document/9249234/ |
| work_keys_str_mv | AT sungyunwoo lowpowerandhighdensityneurondeviceforsimultaneousprocessingofexcitatoryandinhibitorysignalsinneuromorphicsystems AT dongseokkwon lowpowerandhighdensityneurondeviceforsimultaneousprocessingofexcitatoryandinhibitorysignalsinneuromorphicsystems AT nagyongchoi lowpowerandhighdensityneurondeviceforsimultaneousprocessingofexcitatoryandinhibitorysignalsinneuromorphicsystems AT wonmookkang lowpowerandhighdensityneurondeviceforsimultaneousprocessingofexcitatoryandinhibitorysignalsinneuromorphicsystems AT youngtakseo lowpowerandhighdensityneurondeviceforsimultaneousprocessingofexcitatoryandinhibitorysignalsinneuromorphicsystems AT minkyupark lowpowerandhighdensityneurondeviceforsimultaneousprocessingofexcitatoryandinhibitorysignalsinneuromorphicsystems AT jonghobae lowpowerandhighdensityneurondeviceforsimultaneousprocessingofexcitatoryandinhibitorysignalsinneuromorphicsystems AT byunggookpark lowpowerandhighdensityneurondeviceforsimultaneousprocessingofexcitatoryandinhibitorysignalsinneuromorphicsystems AT jongholee lowpowerandhighdensityneurondeviceforsimultaneousprocessingofexcitatoryandinhibitorysignalsinneuromorphicsystems |