2020
DOI: 10.1016/j.sse.2019.107741
|View full text |Cite
|
Sign up to set email alerts
|

Implementation of homeostasis functionality in neuron circuit using double-gate device for spiking neural network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

1
13
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
6
1

Relationship

2
5

Authors

Journals

citations
Cited by 17 publications
(14 citation statements)
references
References 16 publications
1
13
0
Order By: Relevance
“…The Vth difference of the two PF neuron devices on the same die is less than 0.04 V. By adjusting the Vth of the PF neuron by means of a VG3 control strategy or PGM/ERS operation, the Vth variation of neurons can be reduced and the accuracy of the spike rate of the target neuron can be improved. Also, it is possible to mimic the homeostasis function of biological neurons, which is essential in spiking neural networks (SNNs) based on spike-timingdependent-plasticity (STDP) to improve performances [25,26]. T ox = 10 nm L p = 0.7 m Fig.…”
Section: Siomentioning
confidence: 99%
See 1 more Smart Citation
“…The Vth difference of the two PF neuron devices on the same die is less than 0.04 V. By adjusting the Vth of the PF neuron by means of a VG3 control strategy or PGM/ERS operation, the Vth variation of neurons can be reduced and the accuracy of the spike rate of the target neuron can be improved. Also, it is possible to mimic the homeostasis function of biological neurons, which is essential in spiking neural networks (SNNs) based on spike-timingdependent-plasticity (STDP) to improve performances [25,26]. T ox = 10 nm L p = 0.7 m Fig.…”
Section: Siomentioning
confidence: 99%
“…The PF neuron device maintains the nonvolatile of two Vths. The G variation of synaptic devices and the Vth variation of neuron circuits can affect the spike rate of target neurons, which can degrade the performance of HNNs[25,26].Fig. 6 (d)presents the number of dies, showing the difference in the Vth of two PF neuron devices on the same die.…”
mentioning
confidence: 99%
“…24 From another point of view, neuronal inhibition and tunability of ring threshold voltage are important for an energy e cient and reliable neural network. [25][26][27] However, the memristor neurons cannot self-function for control of neuronal inhibition and ring threshold voltage due to the lack of controllability.…”
Section: Introductionmentioning
confidence: 99%
“…However, there is a downside in using conventional flash arrays since require complex external controllers to implement online learning. For this reason, some researchers devised a double-gated synaptic transistor to easily implement online learning such as spike timing-dependent plasticity [15], [40]. The double-gated synaptic transistor mentioned above can realize online learning and lifelong learning, which are the major advantages of hardware-based neuromorphic systems.…”
Section: Introductionmentioning
confidence: 99%
“…Conventional double-gated synaptic devices use output pulse of presynaptic neuron as current source to prevent drain current flowing when only teaching signal is given. However, this method makes the presynaptic neuron to drive an excessive amount of current, causing a fan-out problem [37][38][39][40][41][42]. For example, transmitting spike to one thousand synaptic devices which operate at 1uA each, will require the presynaptic neuron to drive 1mA of current.…”
Section: Introductionmentioning
confidence: 99%