✗ Mechanism failed 2026

Phase-Locked Bursting Cell

Implementation & benchmark of arXiv:2607.02122 — Electronic Bursting Neuron: design, equations and hardware implementation

Usefulness6/10

Difficulty5/10

Novelty7/10

Dynamics Accuracy Sample efficiency Scalability Rnn Ssm Training Dynamical systems Numerical analysis Geometry

Source paper: Electronic Bursting Neuron: design, equations and hardware implementation arXiv:2607.02122 ⓘ · analyzed Aug 30, 2026

AI-generated research hypothesis, automatically tested. Not peer-reviewed.

Idea description

Use the paper's third-order phase-locked-loop equations as a recurrent neuron instead of a leaky integrate-and-fire unit. Emit a spike whenever the phase crosses a chosen threshold, allowing one state trajectory to represent both slow burst envelopes and fast within-burst oscillations.

Formulas

$$\dot{\phi}(t)=y(t),\qquad \dot{y}(t)=z(t),$$ $$\varepsilon_{1}\varepsilon_{2}\dot{z}(t)=\gamma-(\varepsilon_{1}+\varepsilon_{2})z(t)-(1+\varepsilon_{1}\cos(\phi(t)))y(t).$$

$$\phi_{t+1}=\phi_t+\Delta t\,y_t,\qquad y_{t+1}=y_t+\Delta t\,z_t,$$ $$z_{t+1}=z_t+\frac{\Delta t}{\varepsilon_1\varepsilon_2}\left[\gamma+u_t-(\varepsilon_1+\varepsilon_2)z_t-(1+\varepsilon_1\cos\phi_t)y_t\right].$$

$$s_t=H\!\left(\phi_{t+1}-\theta-2\pi k_t\right),\qquad k_t=\left\lfloor\frac{\phi_{t+1}}{2\pi}\right\rfloor,$$ $$\frac{\partial s_t}{\partial \phi_{t+1}}\approx \frac{1}{\alpha}\max\left(0,1-\frac{|\phi_{t+1}-\theta-2\pi k_t|}{\alpha}\right).$$

Mathematical statement

The core model is the phase-locked-loop system $\dot{\phi}(t)=y(t)$, $\dot{y}(t)=z(t)$, and $\varepsilon_1\varepsilon_2\dot{z}(t)=\gamma-(\varepsilon_1+\varepsilon_2)z(t)-(1+\varepsilon_1\cos(\phi(t)))y(t)$. Here $\phi(t)$ is the phase state, $y(t)$ is its first derivative and spike-generating velocity, $z(t)$ is the second derivative and recovery/control state, $\varepsilon_1>0$ and $\varepsilon_2>0$ set two characteristic timescales, and $\gamma$ is a constant drive parameter. The nonlinear term $\cos(\phi)y$ makes the effective damping phase-dependent, while $\varepsilon_1\varepsilon_2$ scales the fastest state dynamics. Add an input current $u_t$ to the $z$-equation and optionally make $\gamma$ a learned affine function of the synaptic input. Euler discretization with step $\Delta t$ yields the recurrent update shown below. Define a spike at a phase crossing, with $H$ the Heaviside function and $k_t$ the completed-cycle index. For backpropagation, use a triangular surrogate derivative of width $\alpha$.

Implementation notes

Integrate the cell at the recurrent-neuron update, after synaptic aggregation and before returning the output spike. Maintain three tensors phi, y, and z with shape [batch, neurons]; let u be the weighted input current at the current time step. Parameterize positive timescales as eps1 = softplus(raw_eps1) + eps_min and eps2 = softplus(raw_eps2) + eps_min. Initially use one learned scalar gamma per neuron; later test gamma = W_gamma @ u + b_gamma. At every time step compute accel = (gamma + u - (eps1 + eps2) * z - (1 + eps1 * cos(phi)) * y) / (eps1 * eps2), then update phi_new = phi + dt * y, y_new = y + dt * z, and z_new = z + dt * accel. Compute k = floor(phi_new / (2*pi)) and emit a hard spike when phi_new - theta - 2*pi*k > 0. During training retain the hard spike in the forward pass but override its derivative with the triangular surrogate in the formula. After a crossing, subtract 2*pi from phi_new rather than resetting all states, preserving burst history. To avoid explicit-Euler instability, begin with dt/(eps1*eps2) <= 0.5, and compare Euler with a semi-implicit or RK2 integrator if states diverge. The equations are taken directly from the paper; input injection, thresholding, phase wrapping, surrogate gradients, and positivity parameterization are adaptations. First test on Sequential-MNIST or SHD using a two-layer SNN, comparing against equal-width LIF and GRU baselines at matched parameter count and simulation steps. Sweep fixed versus learned eps1, eps2, and gamma. Measure accuracy, firing rate, burst length, gradient norm, state boundedness, and loss versus training step. A successful result is higher temporal-task accuracy at equal spike count, or equal accuracy with fewer recurrent neurons or fewer simulation steps, without exploding states or phase drift.

Verification

Mechanism failed

Stage 1 · Toy mechanism gate: Failed ✗

Stage 2 · Mechanism transferred to benchmark: Not tested

Stage 2 · Practical benchmark result: Not run

Methodology: Toy-system gate first; the benchmark stage runs only after a pass. How verification works

Stage 1 — Mechanism check agent confidence 9/10

Built a phase-locked bursting cell with Euler integration, positive learned timescales, phase wrapping, hard crossing spikes, and triangular surrogate gradients, plus a recurrent LIF baseline. The numerical check confirmed first-order Euler error scaling, with error ratios about 2.01 when dt was halved. On the matched toy temporal task, both models reached 100% accuracy; the idea used fewer spikes but had substantially larger states and slightly more parameters, so there was no accuracy win and the sparsity benefit was accompanied by worse state conditioning.

Agent confidence: 9/10

Baseline: accuracy=1.0000, spike_rate=0.3547, max_state=2.9545, params=651, final_loss=0.000389
Idea: accuracy=1.0000, spike_rate=0.01877, max_state=14.6315, params=722, final_loss=0.04216; Euler error ratios=2.0118, 2.0073

Limitations: Only a small synthetic early-versus-late pulse classification task was tested, not Sequential-MNIST, SHD, GRU, matched-FLOP studies, or broad hyperparameter sweeps. The experiment used a short fixed training run and did not separately quantify wall-clock speed, gradient norms, burst lengths, or robustness across random seeds.

How to run: python3 experiment.py

Verdict computed by deterministic test code from paired-seed statistics — not by the language model.

Artifacts

Implementation overview ⬇ Download all as ZIP 3 files · code, reports and structured results

🐍 experiment.py 6.2 KB View Raw
📄 report.md 1.4 KB View
📊 results.json 0.8 KB View Raw