NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation

• URL: http://arxiv.org/abs/2607.15217v1
• Date: Thu, 16 Jul 2026 17:18:59 GMT
• Title: NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation
• Abstract summary: We present NeuronSoup, a neural computation architecture that replaces synchronous layer-by-layer processing with asynchronous, delay-mediated signal propagation.<n>The entire architecture is co-evolved by a genetic algorithm operating on a flat real-valued genome of 14,602 genes.<n>On 10-class MNIST digit classification using frozen ResNet18 features as input, the system evolves a network of 204 active paths through 266 hidden neurons.
• Score: 0.8122270502556375
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present NeuronSoup, a neural computation architecture that replaces synchronous layer-by-layer processing with asynchronous, delay-mediated signal propagation through a pool of shared neurons. Each path in the network routes a continuous-valued signal from one input neuron to one output neuron through a variable number of intermediate hidden neurons. Hidden neurons are physically shared across paths: when two paths pass through the same neuron, the second arrival encounters the accumulated state left by the first, producing constructive or destructive interference that depends on signal polarity and arrival timing. The entire architecture -- topology, weights, delays, and connectivity -- is co-evolved by a genetic algorithm operating on a flat real-valued genome of 14,602 genes. On 10-class MNIST digit classification using frozen ResNet18 features as input, the system evolves a network of 204 active paths through 266 hidden neurons (156 shared across multiple paths, with one neuron participating in 11 distinct paths) and achieves 85.9\% test accuracy after 10,000 generations. The trained model occupies 115 KB. We argue that this architecture addresses fundamental limitations of current deep learning: it requires no differentiable computation graph, adapts its computation depth per-sample, and discovers lateral interactions between processing pathways that current architectures must engineer explicitly. We discuss why genetic algorithms are the correct optimization tool for this problem class, why CMA-ES fails at this scale, and how the architecture generalizes to arbitrary domains by substituting the encoder and output structure.

Related papers

• Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling [55.07411490538404]
  Topological Neural Dynamics (TND) is a sequence modeling framework that shifts from layer-wise to neuron-wise dynamics.<n>TND represents a neural system as a directed neuron graph, an interaction operator, and a local dynamics function.<n>We evaluate TND as a case study on a behavior cloning task in single-player Pong.
  arXiv  Detail & Related papers  (2026-06-19T10:18:24Z)
• Introducing Echo Networks for Computational Neuroevolution [0.32084789957883025]
  We introduce Echo Networks, a type of recurrent network that consists of the connection matrix only.<n>There are no layers, and connections between neurons can be bidirectional but are technically all recurrent.<n>We evaluate Echo Networks successfully on the classification of electrocardiography signals.
  arXiv  Detail & Related papers  (2026-04-09T13:06:25Z)
• Language Model Circuits Are Sparse in the Neuron Basis [50.460651620833055]
  We show that textbfMLP neurons are as sparse a feature basis as SAEs.<n>This work advances automated interpretability of language models without additional training costs.
  arXiv  Detail & Related papers  (2026-01-30T05:41:19Z)
• Gated Parametric Neuron for Spike-based Audio Recognition [26.124844943674407]
  Spiking neural networks (SNNs) aim to simulate real neural networks in the human brain with biologically plausible neurons.<n>This paper proposes a leaky parametric neuron (GPN) to process-temporal information effectively with gating mechanism.
  arXiv  Detail & Related papers  (2024-12-02T03:46:26Z)
• Minimum number of neurons in fully connected layers of a given neural network (the first approximation) [0.0]
  The paper presents an algorithm for searching for the minimum number of neurons in fully connected layers of an arbitrary network solving given problem. The proposed algorithm is the first approximation for estimating the minimum number of neurons in the layer, since, on the one hand, the algorithm does not guarantee that a neural network with the found number of neurons can be trained to the required quality.
  arXiv  Detail & Related papers  (2024-05-23T03:46:07Z)
• Multilayer Multiset Neuronal Networks -- MMNNs [55.2480439325792]
  The present work describes multilayer multiset neuronal networks incorporating two or more layers of coincidence similarity neurons. The work also explores the utilization of counter-prototype points, which are assigned to the image regions to be avoided.
  arXiv  Detail & Related papers  (2023-08-28T12:55:13Z)
• The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks [64.08042492426992]
  We introduce the Expressive Memory (ELM) neuron model, a biologically inspired model of a cortical neuron. Our ELM neuron can accurately match the aforementioned input-output relationship with under ten thousand trainable parameters. We evaluate it on various tasks with demanding temporal structures, including the Long Range Arena (LRA) datasets.
  arXiv  Detail & Related papers  (2023-06-14T13:34:13Z)
• Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits [61.94533459151743]
  This work addresses the challenge of designing neurobiologically-motivated schemes for adjusting the synapses of spiking networks. Our experimental simulations demonstrate a consistent advantage over other biologically-plausible approaches when training recurrent spiking networks.
  arXiv  Detail & Related papers  (2023-03-30T02:40:28Z)
• Increasing biases can be more efficient than increasing weights [33.05856234084821]
  Unit emphasizes the importance of preserving uncorrupted information as it is passed from one unit to the next. We show that by focusing on increasing biases rather than weights, there is potential for significant enhancement in a neural network model's performance.
  arXiv  Detail & Related papers  (2023-01-03T01:36:31Z)
• Saving RNN Computations with a Neuron-Level Fuzzy Memoization Scheme [0.0]
  Recurrent Neural Networks (RNNs) are a key technology for applications such as automatic speech recognition or machine translation. We build a neuron-level fuzzy memoization scheme, which dynamically caches each neuron's output and reuses it whenever it is predicted that the current output will be similar to a previously computed result. We show that our technique avoids more than 26.7% of computations, resulting in 21% energy savings and 1.4x speedup on average.
  arXiv  Detail & Related papers  (2022-02-14T09:02:03Z)
• POPPINS : A Population-Based Digital Spiking Neuromorphic Processor with Integer Quadratic Integrate-and-Fire Neurons [50.591267188664666]
  We propose a population-based digital spiking neuromorphic processor in 180nm process technology with two hierarchy populations. The proposed approach enables the developments of biomimetic neuromorphic system and various low-power, and low-latency inference processing applications.
  arXiv  Detail & Related papers  (2022-01-19T09:26:34Z)
• Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State [66.2457134675891]
  Spiking neural networks (SNNs) are brain-inspired models that enable energy-efficient implementation on neuromorphic hardware. Most existing methods imitate the backpropagation framework and feedforward architectures for artificial neural networks. We propose a novel training method that does not rely on the exact reverse of the forward computation.
  arXiv  Detail & Related papers  (2021-09-29T07:46:54Z)
• Scaling Up Exact Neural Network Compression by ReLU Stability [22.821726425339797]
  We introduce an algorithm based on solving a single optimization problem to identify all stable neurons. Our approach is on median 21 times faster than the state-of-art method.
  arXiv  Detail & Related papers  (2021-02-15T19:19:02Z)
• Non-linear Neurons with Human-like Apical Dendrite Activations [81.18416067005538]
  We show that a standard neuron followed by our novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy. We conduct experiments on six benchmark data sets from computer vision, signal processing and natural language processing.
  arXiv  Detail & Related papers  (2020-02-02T21:09:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.