Silicon Modeling of Spiking Neurons With Diverse Dynamic Behaviors

Ni, Shenglan; Chen, Houpeng; Li, Xi; Lei, Yu; Wang, Qian; Lv, Yi; Zhang, Guangming; Song, Sannian; Zhang, Song

doi:10.1109/tcad.2021.3107245

Cited by 4 publications

(2 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, there has been a notable surge of interest in spike-based models for neurons, making realizing biological neurons one of the most demanding endeavors in neuromorphic engineering. Roughly 90% of the cortex within the human nervous system consists of nonlinear oscillatory neurons [1]. Given the diverse electrophysiological traits observed in biological neurons, various neuron types and firing patterns have been documented [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Compact Low Power Multi-mode Spiking Neuron using Band to Band Tunneling

Kadam,

Singh,

Somappa

et al. 2024

Preprint

View full text Add to dashboard Cite

Efficient and compact neurons with low power consumption are crucial when designing large-scale spiking neural networks (SNNs) for hardware implementation. Many architectures in the literature showcase different spike patterns associated with biological neurons. However, using bulky capacitors to generate the different time constants related to complex neuron patterns makes these circuits area inefficient. This paper presents a band-to-band-tunneling (BTBT) based energy-efficient and compact neuron capable of producing various spike patterns. The BTBT region's extremely low current enables different time constants while eliminating the need of bulky capacitors. The circuit is based on the Izhikevich neuron model. The proposed circuit is designed in Silicon on Insulator technology to exhibit important firing patterns observed in the biological cortex, viz. regular spiking, fast-spiking, and chattering, and it is fine-tuned for efficient operation at low subthreshold voltages. This circuit utilizes only 129 μm 2 area and consumes only 6.7 fJ energy per spike ( approximately 40% lower area and energy per spike than state-of-the-art multi-mode neurons) in G45RFSOI technology.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Consequently, when modeling silicon neurons at a specific level of abstraction, it becomes essential to emphasize the diversity of neuron behaviors. Developing Integrated circuits capable of emulating the diverse temporal dynamics of biological neurons has consistently been a prominent research focus [1], [11]- [15].…”

Section: Introductionmentioning

confidence: 99%