Identifying structural design principles shaping the computational abilities of recurrent neural networks

• URL: http://arxiv.org/abs/2606.23874v1
• Date: Mon, 22 Jun 2026 19:17:25 GMT
• Title: Identifying structural design principles shaping the computational abilities of recurrent neural networks
• Abstract summary: We characterize the computational abilities of recurrent neural networks as a function of their connectivity.<n>For small networks, we constructed the complete catalogs'' of network-function performance.<n>We show that having local 2- and 3-cycles in a network strongly enhances its computational ability.
• Score: 1.5346678870160888
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding how the architecture of neural networks shapes the computations they carry is a central challenge in neuroscience and machine learning. While specific circuit architectures have been linked to particular network computations and theoretical bounds on expressivity of broad classes of networks have been found, we are still missing general principles connecting the structure of finite networks to their computational capabilities. Here, we characterize the computational abilities of recurrent neural networks as a function of their connectivity by training a large collection of different networks to compute a large set of Boolean functions. For small networks, we constructed the complete ``catalogs'' of network-function performance, which revealed that computational capacity varies widely across architectures and that most networks show poor performance, and most functions are hard to compute. However, we show that having local 2- and 3-cycles in a network strongly enhances its computational ability, and networks with such cycles are often the minimal architectures that can solve particular functions. We further show that a small set of structural statistics accurately predict networks' performance. Extending our analysis to large networks showed that typical networks fail even to approximate a randomly selected function. Surprisingly, adding a small number of sparsely connected biologically-inspired interneurons to the network dramatically increases computational capacity. As in small networks, adding short cycles improved networks' capacity, outperforming acyclic or reachability-matched controls. Thus, our results identify local cycles as design principles linking neural connectivity to computational power, and offer a general framework to explore structure-function relations in computing networks.

Related papers

• Deep Lookup Network [76.66809324649154]
  In many resource-limited edge devices, complicated operations can be calculated via lookup tables to reduce computational cost.<n>We introduce a generic and efficient lookup operation which can be used as a basic operation for the construction of neural networks.<n>By replacing computationally expensive multiplication operations with our lookup operations, we develop lookup networks for the image classification, image super-resolution, and point cloud classification tasks.
  arXiv  Detail & Related papers  (2025-09-17T03:31:41Z)
• Effects of structural properties of neural networks on machine learning performance [12.106994960669924]
  This study contributes meaningfully to network science and machine learning, providing insights that could inspire the design of more biologically informed neural networks.<n>Our findings reveal that structural properties do affect performance to some extent. Specifically, networks featuring coherent, densely interconnected communities demonstrate enhanced learning capabilities.
  arXiv  Detail & Related papers  (2025-07-14T07:39:19Z)
• Neuromorphic on-chip reservoir computing with spiking neural network architectures [0.562479170374811]
  Reservoir computing is a promising approach for harnessing the computational power of recurrent neural networks. This paper investigates the application of integrate-and-fire neurons within reservoir computing frameworks for two distinct tasks. We study the reservoir computing performance using a custom integrate-and-fire code, Intel's Lava neuromorphic computing software framework, and via an on-chip implementation in Loihi.
  arXiv  Detail & Related papers  (2024-07-30T05:05:09Z)
• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks [44.31729147722701]
  We show that three-layer neural networks have provably richer feature learning capabilities than two-layer networks.<n>This work makes progress towards understanding the provable benefit of three-layer neural networks over two-layer networks in the feature learning regime.
  arXiv  Detail & Related papers  (2023-05-11T17:19:30Z)
• Max and Coincidence Neurons in Neural Networks [0.07614628596146598]
  We optimize networks containing models of the max and coincidence neurons using neural architecture search. We analyze the structure, operations, and neurons of optimized networks to develop a signal-processing ResNet. The developed network achieves an average of 2% improvement in accuracy and a 25% improvement in network size across a variety of datasets.
  arXiv  Detail & Related papers  (2021-10-04T07:13:50Z)
• Towards Understanding Theoretical Advantages of Complex-Reaction Networks [77.34726150561087]
  We show that a class of functions can be approximated by a complex-reaction network using the number of parameters. For empirical risk minimization, our theoretical result shows that the critical point set of complex-reaction networks is a proper subset of that of real-valued networks.
  arXiv  Detail & Related papers  (2021-08-15T10:13:49Z)
• Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks [50.684661759340145]
  Firefly neural architecture descent is a general framework for progressively and dynamically growing neural networks. We show that firefly descent can flexibly grow networks both wider and deeper, and can be applied to learn accurate but resource-efficient neural architectures. In particular, it learns networks that are smaller in size but have higher average accuracy than those learned by the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-02-17T04:47:18Z)
• Learning low-rank latent mesoscale structures in networks [1.1470070927586016]
  We present a new approach for describing low-rank mesoscale structures in networks. We use several synthetic network models and empirical friendship, collaboration, and protein--protein interaction (PPI) networks. We show how to denoise a corrupted network by using only the latent motifs that one learns directly from the corrupted network.
  arXiv  Detail & Related papers  (2021-02-13T18:54:49Z)
• Computational Separation Between Convolutional and Fully-Connected Networks [35.39956227364153]
  We show how convolutional networks can leverage locality in the data, and thus achieve a computational advantage over fully-connected networks. Specifically, we show a class of problems that can be efficiently solved using convolutional networks trained with gradient-descent.
  arXiv  Detail & Related papers  (2020-10-03T14:24:59Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)
• Neural networks adapting to datasets: learning network size and topology [77.34726150561087]
  We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a gradient-based training. The resulting network has the structure of a graph tailored to the particular learning task and dataset.
  arXiv  Detail & Related papers  (2020-06-22T12:46:44Z)

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.