Journal
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
Volume 70, Issue 11, Pages 4018-4022Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSII.2023.3286810
Keywords
Leaky integrate and fire; SB-MOSFET; SNN; LIF; neuromorphic computing
Categories
Ask authors/readers for more resources
This paper proposes a leaky integrate and fire (LIF) neuron design based on a Schottky Barrier MOSFET (SB-MOSFET) using the Impact Ionization mechanism, which demonstrates considerable improvements in area, energy, and cost. Through 2D calibrated simulation, it is confirmed that the SB-MOSFET LIF neuron is able to precisely replicate the behavior of a neuron without the need for external circuitry. The proposed LIF neuron shows significantly lower energy consumption per spike, approximately 4 pJ/spike, which is the lowest among single transistor-based neurons reported in the literature. Furthermore, it achieves a recognition precision of 89.2% for Modified National Institute of Standards and Technology (MNIST) images. In addition, the SB-MOSFET does not require any doped regions, enabling fabrication with a low thermal budget.
In this brief, a Schottky Barrier MOSFET (SB-MOSFET) based on Impact Ionization mechanism is used to design a leaky integrate and fire (LIF) neuron with considerable enhancement in area, energy and cost is proposed. Using 2D calibrated simulation, we confirmed that SB-MOSFET LIF is able to replicate the neuron behavior precisely without using external circuitry. The proposed LIF neuron shows significantly lower energy per spike of similar to 4 pJ/spike, which is lowest among the single transistor based neurons present in the literature. The recognition precision of 89.2% has been accomplished for Modified National Institute of Standards and Technology (MNIST) image. Besides this, SB-MOSFET doesn't require any doped regions, therefore it can be fabricated with low thermal budget.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available