Spiking recurrent neural networks (SRNNs) rival gated recurrent neural networks (RNNs) on various tasks, yet they still lack several hallmarks of biological neural networks. We introduce a biologically grounded SRNN that implements Dale's law with conductance-based stands for a-amino-3-hydroxy-5-methyl-4-isoxazolepropionic acid (AMPA) and gamma-aminobutyric acid (GABA) reversal potentials. These reversal potentials modulate synaptic gain as a function of the postsynaptic membrane potential, and we derive theoretically how they make each neuron's effective dynamics and subthreshold resonance input-dependent. We trained SRNNs on the Spiking Heidelberg Digits (SHD) dataset and show that SRNNs with reversal potentials reduce spike energy by up to 3 × , while maintaining, or increasing, task accuracy. This leads to high-performing Dalean SRNNs that substantially improve on Dalean networks without reversal potentials. SRNNs with reversal potentials exhibited spike-train statistics closer to Poisson statistics, similar to biological neurons, and showed a substantial reduction in oscillatory activity, leading to increased heterogeneity in response properties. Thus, Dale's law with reversal potentials, a core feature of biological neural networks, can render SRNNs more accurate and energy-efficient.
Understanding how biological neural networks are shaped via local plasticity mechanisms can lead to energy-efficient and self-adaptive information processing systems, which promises to mitigate some of the current roadblocks in edge computing systems. While biology makes use of spikes to seamless use both spike timing and mean firing rate to modulate synaptic strength, most models focus on one of the two. In this work, we present a Hebbian local learning rule that models synaptic modification as a function of calcium traces tracking neuronal activity. We show how the rule reproduces results from spike time and spike rate protocols from neuroscientific studies. Moreover, we use the model to train spiking neural networks on MNIST digit recognition to show and explain what sort of mechanisms are needed to learn real-world patterns. We show how our model is sensitive to correlated spiking activity and how this enables it to modulate the learning rate of the network without altering the mean firing rate of the neurons nor the hyparameters of the learning rule. To the best of our knowledge, this is the first work that showcases how spike timing and rate can be complementary in their role of shaping the connectivity of spiking neural networks.
Willian Soares Girāo, Nicoletta Risi, Caroline Geisler et al.· Neuromorphic Computing and E...· 0 citations
This work proposes Burst Spiking Neural Networks (BuSNNs), built upon Burst-enhanced Spiking Neurons and a Dynamic Weight Constraint (DWC) mechanism, which mitigates perturbation-induced transitions in activation states and thereby enhances robustness.
Jiahong Zhang, Sijun Shen, Man Yao et al.· 0 citations
This work proposes a noisy group neuron (NGN) model, which incorporates population-level synchronous resetting and neural stochasticity as fundamental computational mechanisms, and develops the NGN method as a framework that combines the NGN model with backpropagation learning based on mean-field dynamics.
Yajie Zhai, Yanmei Kang, Meng Li et al.· 0 citations
Spiking Neural Networks (SNNs) represent a biologically grounded computational paradigm in which information is carried by discrete spike events, conferring structural compatibility with low-power, event-driven neuromorphic hardware. A persistent impediment to realising the full energy benefit of SNNs in practice is the near-universal adoption of fixed firing thresholds, which prevent individual neurons from self-regulating their activity and permit task-irrelevant spike generation to accumulate unchecked. This paper introduces and evaluates a Homeostatically Regulated Adaptive Threshold (HAT) mechanism in which each neuron’s firing threshold is updated at every time step in proportion to the deviation between its exponentially smoothed firing rate and a designer-specified target rate. The rule is derived from the proportional control framework and mirrors the intrinsic excitability regulation observed in biological cortical circuits. A novel metric, the Target Achievement Error (TAE), is defined to quantify how faithfully the population reaches its intended operating point. Computational cost is assessed using a synaptic operations (SynOps) proxy that is hardware-agnostic and scales linearly with spike volume. A two-stage screening procedure selects the best configurations from 27 candidates by first enforcing an accuracy constraint and then ranking them by spike reduction, TAE, energy, and accuracy. Controlled experiments on MNIST show that the fixed-threshold baseline attains a mean validation accuracy of 92.52%±1.13% across three random seeds, with an average of 21.86 × 106 spikes and an estimated SynOps energy of 211.70 mJ. The top-ranked homeostatic configuration (α = 0.1, ftarget = 0.1, γ = 0.2) achieves 92.02% validation accuracy with a 15.54% reduction in total spike activity, incurring only a 0.50% absolute accuracy shortfall. These results indicate that homeostatic threshold regulation offers a structurally non-invasive route to improved inference energy in gradient-trained SNNs.
Gripsy Paul Mannickathan, Yeldo K. Varghese, Sahala Mariyam P. S. et al.· Journal of Network and Infor...· 0 citations
Spiking neural networks (SNNs) offer an energy-efficient alternative to traditional neural networks by utilizing discrete, temporally precise spike events. However, this study identifies a critical vulnerability in SNNs on recently established bit-based codes: consistent performance degradation when temporal spike encoding orders are reversed, such as using least-significant-bit ordering instead of most-significant-bit. We theoretically formalize this phenomenon as premature state annihilation, wherein early noisy spikes in information-discordant encodings trigger hard resets in leaky integrate-and-fire (LIF) neurons. These resets erase accumulated membrane state and, because the effective temporal influence of an input is largest for early timesteps, leave the backpropagated learning signal concentrated where the information is not. We measure the per-timestep class-mutual-information profile of six encodings directly, without reference to network accuracy, and show that the resulting concordance ordering predicts the observed degradation. While dense codes like weighted phase encoding suffer catastrophic drops (up to 48%), sparse codes like time-to-first-spike remain robust, and exchangeable rate codes are provably invariant to reversal. We evaluate several mitigation strategies, finding that parametric LIF (PLIF) neurons and aggressive membrane leakage significantly recover performance by adapting to or suppressing early noise.
Nhan Trong Luu, Duong Trung Luu, Nam Ngoc Pham et al.· Neuromorphic Computing and E...· 0 citations
We introduce a hardware circuit model that implements spike-time dependent plasticity (STDP) to endow spiking neural networks with learning capabilities. Our circuit model is characterized as both minimal and bio-inspired, due to its simplicity and to a novel active dendrite compartment that mimics the synaptic potentiation mechanism. The active dendrite consists of an integrate-and-fire stage which produces a train of pulses whose number is inversely related to the timing between pre- and post-synaptic spikes. The dendrite pulses modulate in a reliable manner the synaptic efficacy (conductance) that we implemented with a digipot, considered as an idealized non-volatile memristor. We demonstrate the behavior of the circuit by implementing a minimal spiking neuron model of associative learning by STDP, which is analog to the classic conditioning experiment of Pavlov’s dog.
Adrien D’hollande, Olivier Schneegans, Kang Wang et al.· Neuromorphic Computing and E...· 0 citations