- Rating
- 3
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The authors introduce a unified state-space framework to compare different spiking neuron models, which leads to the design of a time-variant multi-compartment neuron. This new neuron model pairs multiscale oscillatory states with input-driven gates that control state transitions, input integration, and readout. Empirically, the approach delivers competitive accuracy on temporal classification benchmarks and shows clear advantages on synthetic memory tasks, with additional ablation and generalization studies backing up the design of the modulation mechanisms.
Critical strengths
- The results on selective copying and associative recall really stand out. TV-MCN achieves large gains here, and seeing this advantage hold consistently across several tasks under a unified network architecture makes the empirical contribution hard to ignore.
- The evaluation goes beyond simple test accuracy with well-designed memory probes. The delayed-recall and sequence-length experiments are particularly helpful. By padding the input with distractors while preserving the underlying target sequence, the authors directly test the exact state-retention capability that motivates their model.
Critical weaknesses
- It is not entirely clear what sets this model apart from selective SSMs such as Mamba. Having input-driven , , and parameters is already the defining feature of Mamba. The authors need to do a much better job of explaining what the spiking realization specifically adds on top of standard selective state spaces.
- The math behind the reset dynamics is not spelled out clearly enough. Since the somatic membrane potential is just a readout , saying it undergoes a soft reset only tells us what happens to , without specifying how the persistent internal state is updated upon firing.
Questions for authors
- Could you write out the exact reset function used in TV-MCN and clarify which post-reset states actually carry over into the next time step? Also, please specify the exact dimensions of , , and .
- Conceptually and mathematically, what sets TV-MCN apart from a complex-valued selective SSM with a spiking readout bolted on at the end? Including a direct comparison or discussion of the model with and without the spiking and reset mechanisms would really help clarify where the core novelty lies.
2 comments
2. Relationship between our method and Selective SSM & Mamba
We thank the reviewer for pointing out the connection between TV-MCN and Selective SSM. We acknowledge that our method draws on Selective SSM in terms of parameterization, and we would like to take this opportunity to clarify the motivation and core contributions of our work.
The main contribution of this paper is to summarize existing spiking neuron designs within a unified state-dynamics framework and, based on this framework, identify an overlooked issue: the state evolution, information writing, and state readout of existing neurons typically still follow fixed rules. Therefore, we aim to investigate whether introducing time-varying dynamics can further improve the temporal information processing capabilities of individual spiking neurons. Within this framework, a time-varying spiking neuron can be expressed as:
The key idea behind this research direction is to allow the neuron's dynamical rules to change over time, and dynamically adjusting these rules according to the current input is one particular approach explored in this paper (other possible approaches include adjusting these rules based on the neuron's internal state itself rather than its input). To this end, TV-MCN adopts the input-dependent parameterization of , , and previously studied in Selective SSM. However, our research consistently focuses on the design of the internal dynamics of individual spiking neurons, and does not adopt Mamba's input and output projections, local causal convolutions, nonlinear activations, gating branches, residual connections, normalization, or other such architectural designs.
Therefore, the goal of this paper is not to improve performance by adding spike generation and reset mechanisms to Mamba; these mechanisms are already integral components of spiking neurons. What we aim to investigate is how modifying a neuron's internal dynamical rules can improve its temporal processing capabilities. The input-dependent parameterization used in Selective SSM is simply an established approach that we can draw upon.
To further verify that this idea does not depend on the specific parameterization of Selective SSM, we introduce an additional input-dependent design that directly generates , , and from the current input, allowing the neuron's state evolution, input integration, and state readout to vary over time without introducing a dynamic . The specific parameterization is as follows:
With all other experimental settings unchanged, this design also achieves competitive results across tasks. On MAD ICR and MAD Noisy ICR, it achieves 98.88% (-1.12 pp) and 99.22% (-0.77 pp), respectively, and reaches 100% (+1.60 pp) word accuracy on STORE--RECALL. On GSC, SHD, SSC, and DVS128 Gesture, it achieves 90.59% (+0.03 pp), 89.05% (+0.75 pp), 73.22% (+2.24 pp), and 91.67% (-2.08 pp), respectively. The values in parentheses indicate the differences in accuracy relative to the original TV-MCN with input-dependent , , and .
These additional experiments further demonstrate that the effectiveness of time-varying dynamics in the input-dependent setting investigated in this paper is not limited to the parameterization used in Selective SSM. We thank the reviewer for raising this important question and for the opportunity to clarify the motivation and contributions of our work.
1. Spiking Neuron Reset Mechanism and Parameter Dimensions
We sincerely thank the reviewer for the careful evaluation of our work and the constructive suggestions. We address each concern below.
We thank the reviewer for pointing out that the descriptions of the reset mechanism and parameter dimensions were not sufficiently clear. We provide further clarification below.
In TV-MCN, the complex-valued multi-compartment state ht evolves continuously and is read out through Ct to provide input to the soma. The soma accumulates this input in a separate membrane potential state and performs a soft reset after spike generation:
utvt−stvt+=Re(Ctht),=vt−1++ut,=H(vt−−ϑ),=vt−−ϑst.
The reset only affects the somatic membrane potential and does not alter the multi-compartment state. Therefore, the reset mapping for the state is Rh(ht,st)=ht. At the next time step, both ht and the reset membrane potential vt+ are retained and used for subsequent state evolution and somatic integration, respectively.
Regarding parameter dimensions, for a single neuron containing N compartments:
xt∈R,ht∈CN,Bt∈CN×1,Ct∈C1×N.
Here, xt is the scalar input current received by the neuron, while Bt and Ct are generated from the complete input vector xt∈RD of the current layer.