Causal Learning with Neural Assemblies

• URL: http://arxiv.org/abs/2604.26919v1
• Date: Wed, 29 Apr 2026 17:34:33 GMT
• Title: Causal Learning with Neural Assemblies
• Abstract summary: We show that projection, local plasticity control, and sparse winner selection are sufficient for directional learning.<n>We introduce DIRECT, a mechanism that co-activates source and target assemblies under an adaptive gain schedule to internalize directed relations.<n>Results establish neural assemblies as an auditable bridge between biologically plausible dynamics and formal causal models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Can Neural Assemblies -- groups of neurons that fire together and strengthen through co-activation -- learn the direction of causal influence between variables? While established as a computationally general substrate for classification, parsing, and planning, neural assemblies have not yet been shown to internalize causal directionality. We demonstrate that the inherent operations of neural assemblies -- projection, local plasticity control, and sparse winner selection -- are sufficient for directional learning. We introduce DIRECT (DIRectional Edge Coupling/Training), a mechanism that co-activates source and target assemblies under an adaptive gain schedule to internalize directed relations. Unlike backpropagation-based methods, DIRECT relies solely on local plasticity, making the resulting causal claims auditable at the mechanism level. Our findings are verified through a dual-readout validation strategy: (i) synaptic-strength asymmetry, measuring the emergent weight gap between forward and reverse links, and (ii) functional propagation overlap, quantifying the reliability of directional signal flow. Across multiple domains, the framework achieves perfect structural recovery under a supervised, known-structure setting. These results establish neural assemblies as an auditable bridge between biologically plausible dynamics and formal causal models, offering an "explainable by design" framework where causal claims are traceable to specific neural winners and synaptic asymmetries.

Related papers

• CDS: Counterfactual Directionality Score for Structured Interventions in Spatial Graphs [0.0]
  We introduce a framework for structured counterfactual interventions in graph-based models to estimate directional influence between node types.<n>Our approach trains a Neighbor Influence Model (NIM) to predict node states from local neighborhoods.<n>We define the Counterfactual Directionality Score (CDS), which measures the change in predicted node state induced by targeted perturbations.
  arXiv  Detail & Related papers  (2026-07-15T07:02:33Z)
• Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion [12.63651664394193]
  We propose a novel reinforcement learning framework that encourages the disentanglement of dynamics-specific and reward-specific features.<n>We show that our method improves learning efficiency and overall performance compared to conventional RL approaches.
  arXiv  Detail & Related papers  (2026-06-16T20:28:39Z)
• Beyond representational alignment with brain-guided language models for robust reasoning [51.87370932573858]
  We show that large language models (LLMs) align with neural signals from reasoning-related regions.<n>Using a neural-predictivity metric, we find that LLMs explain a substantial fraction of the explainable variance in reasoning-related regions.<n>We propose a brain-guided framework: we steer model representations along directions induced by the joint structure of model and brain representations.
  arXiv  Detail & Related papers  (2026-06-10T10:22:49Z)
• Neuronal Group Communication for Efficient Neural representation [85.36421257648294]
  This paper addresses the question of how to build large neural systems that learn efficient, modular, and interpretable representations.<n>We propose Neuronal Group Communication (NGC), a theory-driven framework that reimagines a neural network as a dynamical system of interacting neuronal groups.<n>NGC treats weights as transient interactions between embedding-like neuronal states, with neural computation unfolding through iterative communication among groups of neurons.
  arXiv  Detail & Related papers  (2025-10-19T14:23:35Z)
• Disentangling Recall and Reasoning in Transformer Models through Layer-wise Attention and Activation Analysis [3.1526281887627587]
  Distinguishing recall from reasoning is crucial for predicting model generalization.<n>We use controlled datasets of synthetic linguistic puzzles to probe transformer models at the layer, head, and neuron level.<n>Our results provide the first causal evidence that recall and reasoning rely on separable but interacting circuits in transformer models.
  arXiv  Detail & Related papers  (2025-10-03T04:13:06Z)
• Self-Supervised Discovery of Neural Circuits in Spatially Patterned Neural Responses with Graph Neural Networks [0.0]
  Inferring synaptic connectivity from neural population activity is a fundamental challenge in computational neuroscience.<n>We propose a graph-based neural inference model that simultaneously predicts neural activity and infers latent connectivity by modeling neurons as interacting nodes in a graph.
  arXiv  Detail & Related papers  (2025-09-21T17:46:43Z)
• Allostatic Control of Persistent States in Spiking Neural Networks for perception and computation [79.16635054977068]
  We introduce a novel model for updating perceptual beliefs about the environment by extending the concept of Allostasis to the control of internal representations.<n>In this paper, we focus on an application in numerical cognition, where a bump of activity in an attractor network is used as a spatial numerical representation.
  arXiv  Detail & Related papers  (2025-03-20T12:28:08Z)
• Connectivity structure and dynamics of nonlinear recurrent neural networks [41.038855001225826]
  We develop a theory to analyze how connectivity structure shape high-dimensional collective activity in neural networks.<n>We show that connectivity structure can be invisible in single-neuron activities while dramatically shaping collective activity.
  arXiv  Detail & Related papers  (2024-09-03T15:08:37Z)
• Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation [56.34634121544929]
  In this study, we first construct the brain-effective network via the dynamic causal model. We then introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE) This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks.
  arXiv  Detail & Related papers  (2024-05-21T20:37:07Z)
• Interpreting Neural Policies with Disentangled Tree Representations [58.769048492254555]
  We study interpretability of compact neural policies through the lens of disentangled representation. We leverage decision trees to obtain factors of variation for disentanglement in robot learning. We introduce interpretability metrics that measure disentanglement of learned neural dynamics.
  arXiv  Detail & Related papers  (2022-10-13T01:10:41Z)
• Learning Neural Causal Models with Active Interventions [83.44636110899742]
  We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting. We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
  arXiv  Detail & Related papers  (2021-09-06T13:10:37Z)
• The Causal Neural Connection: Expressiveness, Learnability, and Inference [125.57815987218756]
  An object called structural causal model (SCM) represents a collection of mechanisms and sources of random variation of the system under investigation. In this paper, we show that the causal hierarchy theorem (Thm. 1, Bareinboim et al., 2020) still holds for neural models. We introduce a special type of SCM called a neural causal model (NCM), and formalize a new type of inductive bias to encode structural constraints necessary for performing causal inferences.
  arXiv  Detail & Related papers  (2021-07-02T01:55:18Z)
• Complementary Structure-Learning Neural Networks for Relational Reasoning [3.528645587678267]
  We show that pattern separation in the hippocampus allows rapid learning in novel environments. slower learning in neocortex accumulates small weight changes to extract systematic structure from well-learned environments.
  arXiv  Detail & Related papers  (2021-05-19T06:25:21Z)
• Online neural connectivity estimation with ensemble stimulation [5.156484100374058]
  We propose a method based on noisy group testing that drastically increases the efficiency of this process in sparse networks. We show that it is possible to recover binarized network connectivity with a number of tests that grows only logarithmically with population size. We also demonstrate the feasibility of inferring connectivity for networks of up to tens of thousands of neurons online.
  arXiv  Detail & Related papers  (2020-07-27T23:47:03Z)

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.