SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.14549 · NeurIPS · 2021

Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons

Paul Haider, Benjamin Ellenberger, Laura Kriener, Jakob Jordan, Walter Senn, Mihai Petrovici

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2110.14549.json · badge: /api/ran/2110.14549.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
unibe-cns/le_NeurIPS_code community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
LEDynamics Ran
ran on a synthesized input · constructed an object; no result was computed
unibe-cns/le_NeurIPS_code/fig2a_fourier_synthesis/le_dynamics.py
code served (permissive licence) · get_code("8f78ca5759b57c3b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, LEDynamics: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleConnection(nn.Module):
    """Minimal connection module that satisfies the interface used in LEDynamics"""
    
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.weight = nn.Parameter(torch.randn(output_dim, input_dim))
    
    def forward(self, r_bottom):
        """Compute input current from bottom layer activity"""
        return torch.matmul(r_bottom, self.weight.t())
    
    def __call__(self, r_bottom):
        """Called as self.conn(r_bottom) in LEDynamics"""
        return self.forward(r_bottom)
    
    def compute_grad(self, r_bottom, e):
        """Compute gradient (stub implementation)"""
        pass
    
    def compute_error(self, r_bottom, e):
        """Compute error to backpropagate (returns error shaped like r_bottom)"""
        return torch.matmul(e, self.weight)


# Create a simple connection: 4 (input) -> 3 (output)
conn = SimpleConnection(input_dim=4, output_dim=3)

# Activation function and its derivative
def phi(x):
    return torch.relu(x)

def phi_prime(x):
    return (x > 0).float()

ARGS = {
    'conn': conn,
    'tau': 10.0,
    'dt': 0.1,
    'tau_e': 1.0,
    'phi': phi,
    'phi_prime': phi_prime,
    'gamma': 1.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LEDynamics — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a LEDynamics output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The response time of physical computational elements is finite, and neurons are no exception. In hierarchical models of cortical networks each layer thus introduces a response lag. This inherent property of physical dynamical systems results in delayed processing of stimuli and causes a timing mismatch between network output and instructive signals, thus afflicting not only inference, but also learning. We introduce Latent Equilibrium, a new framework for inference and learning in networks of slow components which avoids these issues by harnessing the ability of biological neurons to phase-advance their output with respect to their membrane potential. This principle enables quasi-instantaneous inference independent of network depth and avoids the need for phased plasticity or computationally expensive network relaxation phases. We jointly derive disentangled neuron and synapse dynamics from a prospective energy function that depends on a network's generalized position and momentum. The resulting model can be interpreted as a biologically plausible approximation of error backpropagation in deep cortical networks with continuous-time, leaky neuronal dynamics and continuously active, local plasticity. We demonstrate successful learning of standard benchmark datasets, achieving competitive performance using both fully-connected and convolutional architectures, and show how our principle can be applied to detailed models of cortical microcircuitry. Furthermore, we study the robustness of our model to spatio-temporal substrate imperfections to demonstrate its feasibility for physical realization, be it in vivo or in silico.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2110.14549")
get_code_for_paper("2110.14549")
have("2110.14549")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2110.14549.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2110.14549.svg)](https://syntology.ai/paper/2110.14549)

Connect an agent — have() is free.