A Deep Dive into the Design Space of a Dynamically Reconfigurable Cryogenic Spiking Neuron

Md Mazharul Islam; Shamiul Alam; Catherine D Schuman; Md Shafayat Hossain; Ahmedullah Aziz

Home/Archive/arXiv

arXiv · 2308.15754

A Deep Dive into the Design Space of a Dynamically Reconfigurable Cryogenic Spiking Neuron

Md Mazharul Islam·Shamiul Alam·Catherine D Schuman·Md Shafayat Hossain·Ahmedullah Aziz

View original source ↗Read source document ↗Export metadata ↓

Abstract

Spiking neural network offers the most bio-realistic approach to mimic the parallelism and compactness of the human brain. A spiking neuron is the central component of an SNN which generates information-encoded spikes. We present a comprehensive design space analysis of the superconducting memristor (SM)-based electrically reconfigurable cryogenic neuron. A superconducting nanowire (SNW) connected in parallel with an SM function as a dual-frequency oscillator and two of these oscillators can be coupled to design a dynamically tunable spiking neuron. The same neuron topology was previously proposed where a fixed resistance was used in parallel with the SNW. Replacing the fixed resistance with the SM provides an additional tuning knob with four distinct combinations of SM resistances, which improves the reconfigurability by up to ~70%. Utilizing an external bias current (Ibias), the spike frequency can be modulated up to ~3.5 times. Two distinct spike amplitudes (~1V and ~1.8 V) are also achieved. Here, we perform a systematic sensitivity analysis and show that the reconfigurability can be further tuned by choosing a higher input current strength. By performing a 500-point Monte Carlo variation analysis, we find that the spike amplitude is more variation robust than spike frequency and the variation robustness can be further improved by choosing a higher Ibias. Our study provides valuable insights for further exploration of materials and circuit level modification of the neuron that will be useful for system-level incorporation of the neuron circuit

Explore related subjects

cs.NE cond-mat.mes-hall

Keep this discovery

BibTeX RIS

Md Mazharul Islam, Shamiul Alam, Catherine D Schuman, Md Shafayat Hossain, Ahmedullah Aziz. 2023-08-30. A Deep Dive into the Design Space of a Dynamically Reconfigurable Cryogenic Spiking Neuron. https://arxiv.org/abs/2308.15754

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution

Evolvable-Substrate HyperNEAT (ES-HyperNEAT), a bio-inspired indirect encoding that determines neuron placement and connection weights from spatial coordinates, exhibits a failure mode on MNIST as a diagnostic benchmark. Because input pixels map to a coordinate space centered at the origin, evolved networks converge on a small central cluster of input pixels, a spatial-concentration bias; prior work observed only 21% mean accuracy in this regime. Is this bias an optimization artifact or an architectural ceiling? Inspired by Mixture-of-Experts (MoE) principles, we partition the input into non-overlapping spatial segments, each assigned to a separately evolved specialist network. With 13 such experts, this design reaches 43% mean accuracy, a 106% relative improvement over the baseline. The architectural gain does not depend on data-driven aggregation: equal-weighted averaging, which uses no validation data, already yields a 70% improvement; the gain comes from partitioning, not the weighting. Receptive-field analysis shows the mechanism: partitioning forces evolution to discover features across the entire image, expanding active pixel coverage from 4% to 79%. Absolute accuracy stays below gradient-trained baselines, but the relative gain points to central bias, not the evolutionary search. Two tools are designed to generalize beyond MNIST: a receptive-field diagnostic for silent input-coverage collapse, and a spatial-partitioning remedy that restores coverage.

cs.NE↗

arXiv2026

A Bio-Plausible Visual Neural Network for Locust-Inspired Collision Perception

Locust visual systems have long served as an important biological paradigm for studying looming perception and collision avoidance. Numerous computational models have successfully reproduced the selective responses of Lobula Giant Movement Detector (LGMD) neurons to approaching objects, thereby emulating the fundamental functionality of the biological system. However, existing models remain limited in biological plausibility and robustness when operating in complex and dynamic visual environments. To address these limitations, we propose a biologically plausible neural network for locust-inspired looming detection. The proposed framework incorporates a spatially isotropic sampling strategy that mimics the ommatidial organization of the locust compound eye, a population-voting mechanism inspired by population coding in biological neural systems, and leaky integrate-and-fire neuronal dynamics to replace conventional sigmoid-based membrane activation. Systematic experiments on synthetic stimuli, laboratory sequences, and real-world driving scenarios demonstrate that the proposed model improves robustness under challenging visual conditions while preserving computational efficiency and enhancing biological fidelity. These results highlight the potential of biologically grounded neural computation for robust and efficient collision perception.

cs.NE↗

arXiv2026

Structural Fusion of Bayesian Networks with Limited Treewidth Using Genetic Algorithms

This paper introduces an evolutionary computation approach for consensus in structural Bayesian Network (BN) fusion under the constraint of limited treewidth. The consensus BN aims to reconcile multiple input BNs into a single one that retains key structural features present in the original networks. Treewidth, a graph-based parameter associated with computationally tractable inference, is utilized to restrict the complexity of the resulting network. A genetic algorithm is proposed to look for a BN that codifies as much information about the unrestricted fusion as possible while ensuring the treewidth restriction. Experimental evaluation demonstrates the genetic algorithm's ability to obtain consensus BNs with limited treewidth, providing a valuable tool for aggregating information from diverse sources while returning a computationally actionable model.

cs.NE↗