An ultra-compact leaky integrate-and-fire neuron with long and tunable time constant utilizing pseudo resistors for spiking neural networks

Spiking neural networks (SNNs) inspired by biological neurons enable a more realistic mimicry of the human brain. To realize SNNs similar to large-scale biological networks, neuron circuits with high area efficiency are essential. In this paper, we propose a compact leaky integrate-and-fire (LIF) neuron circuit with a long and tunable time constant, which consists of a capacitor and two pseudo resistors (PRs). The prototype chip was fabricated with TSMC 65 nm CMOS technology, and it occupies a die area of 1392 m2. The fabricated LIF neuron has a power consumption of 6 W and a leak time constant of up to 1.2 ms (the resistance of PR is up to 600 MΩ). In addition, the time constants are tunable by changing the bias voltage of PRs. Overall, this proposed neuron circuit facilitates the very-large-scale integration (VLSI) of adaptive SNNs, which is crucial for the implementation of bio-scale brain-inspired computing.

Quantum Tunnelling based Ultra-compact and Energy Efficient Spiking Neuron enables Hardware Liquid State Machine

Low-power and low-area neurons are essential for hardware implementation of large-scale SNNs. Various novel physics based leaky-integrate-and-fire (LIF) neuron architectures have been proposed with low power and area, but are not compatible with CMOS technology to enable brain scale implementation of SNN. In this paper, for the first time, we demonstrate hardware implementation of LSM reservoir using band-to-band-tunnelling (BTBT) based neuron. A low-power thresholding circuit and current-to-voltage converter design are proposed. We further propose a predistortion technique to linearize a nonlinear neuron without any area and power overhead. We establish the equivalence of the proposed neuron with the ideal LIF neuron to demonstrate its versatility. To verify the effect of the proposed neuron, a 36-neuron LSM reservoir is fabricated in GF-45nm PDSOI technology. We achieved 5000x lower energy-per-spike at a similar area, 50x less area at a similar energy-per-spike, and 10x lower standby power at a similar area and energy-per-spike. Such overall performance improvement enables brain scale computing.

Artificial Neurons Based on Ag/V2C/W Threshold Switching Memristors

Artificial synapses and neurons are two critical, fundamental bricks for constructing hardware neural networks. Owing to its high-density integration, outstanding nonlinearity, and modulated plasticity, memristors have attracted emerging attention on emulating biological synapses and neurons. However, fabricating a low-power and robust memristor-based artificial neuron without extra electrical components is still a challenge for brain-inspired systems. In this work, we demonstrate a single two-dimensional (2D) MXene(V2C)-based threshold switching (TS) memristor to emulate a leaky integrate-and-fire (LIF) neuron without auxiliary circuits, originating from the Ag diffusion-based filamentary mechanism. Moreover, our V2C-based artificial neurons faithfully achieve multiple neural functions including leaky integration, threshold-driven fire, self-relaxation, and linear strength-modulated spike frequency characteristics. This work demonstrates that three-atom-type MXene (e.g., V2C) memristors may provide an efficient method to construct the hardware neuromorphic computing systems.

LIF Neuron with Hypo-exponential Distributed Delay: Emergence of Unimodal, Bimodal, Multimodal ISI Distribution with Long Tail

Background: Distributed Delay Framework (DDF) has suggested a mechanism to incorporate the delay factor in the evolution of the membrane potential of a neuron model in terms of distributed delay kernel functions. Incorporation of delay in neural networks provide comparatively more efficient output. Depending on the parameter of investigation, there exist a number of choices of delay kernel function for a neuron model. Objective: We investigate the Leaky integrate-and-fire (LIF) neuron model in DDF with hypoexponential delay kernel. LIF neuron with hypo-exponential distributed delay (LIFH) model is capable to regenerate almost all possible empirically observed spiking patterns. Methods: In this article, we perform the detailed analytical and simulation based study of the LIFH model. We compute the explicit expressions for the membrane potential and its first two moment viz. mean and variance, in analytical study. Temporal information processing functionality of the LIFH model is investigated during simulation based study. Results: We find that the LIFH model is capable to reproduce unimodal, bimodal and multimodal inter-spike- interval distributions which are qualitatively similar with the experimentally observed ISI distributions. Conclusion: We also notice the neurotransmitter imbalance situation, where a noisy neuron exhibits long tail behavior in aforementioned ISI distributions which can be characterized by power law behavior.