Treffer: A bio-inspired ferroelectric tunnel FET-based spiking neuron for high-speed energy efficient neuromorphic computing.

In this study, a novel spiking neuron based on double-gate ferroelectric tunnel field effect transistor (DG-FE-TFET) is proposed in the 50 nm technology node. Through calibrated simulations in Atlas TCAD, it is verified that by leveraging the forward transfer characteristics, the device accurately emulates the spiking patterns exhibited by biological neurons. The device works on tunneling mechanism which ensures low voltage operation and thereby reduces overall energy consumption. The proposed neuron consumes an energy of 0.58 aJ per spike, which is 1.29, 41.38, 7.75 × 105, 12.9 × 105, 1.89 × 105, 13.79 × 106, and 7.75 × 107 times lesser than V-DGTFET, FE-JLFET, Z2-FET, DG-TFET, FD-MOSFET, Ge-MOSFET, and Si-MOSFET. Notably, the neuron operates without the need for additional reset circuitry and achieves spiking frequency of 344 GHz, which can be attributed to the sharp switching characteristics of the proposed device. This greatly simplifies implementation and facilitates a higher neuron density for energy-efficient neuromorphic chips with high-speed capabilities. Finally, based upon the proposed neuron, a multi-layer spiking neural network (SNN) is designed in Python platform. The network is implemented for signal classification with an accuracy of 84.4%. • A novel spiking neuron based on double-gate ferroelectric tunnel field effect transistor is proposed. • The device works on tunneling mechanism which ensures low voltage operation with an energy consumption of 0.58 aJ per spike. • The neuron operates without the need for external reset circuitry and achieves spiking frequency of 344 GHz. • Based upon the proposed neuron, a spiking neural network is designed for signal classification with an accuracy of 84.4%. [ABSTRACT FROM AUTHOR]