From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips

• URL: http://arxiv.org/abs/2603.22770v1
• Date: Tue, 24 Mar 2026 03:53:04 GMT
• Title: From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips
• Abstract summary: In this work, we study resilience as a structural property of neural architectures.<n>We show that lower precision, higher sparsity, bounded activations, and shallow depth are consistently favored.<n>We identify a novel even-layer recovery effect unique to logic-based architectures.
• Score: 0.6868507883617846
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors. While empirical studies indicate that reducing numerical precision can improve fault tolerance, the theoretical basis of this phenomenon remains underexplored. In this work, we study resilience as a structural property of neural architectures rather than solely as a property of a dataset-specific trained solution. By deriving the expected squared error (MSE) under independent parameter bit flips across multiple numerical formats and layer primitives, we show that lower precision, higher sparsity, bounded activations, and shallow depth are consistently favored under this corruption model. We then argue that logic and lookup-based neural networks realize the joint limit of these design trends. Through ablation studies on the MLPerf Tiny benchmark suite, we show that the observed empirical trends are consistent with the theoretical predictions, and that LUT-based models remain highly stable in corruption regimes where standard floating-point models fail sharply. Furthermore, we identify a novel even-layer recovery effect unique to logic-based architectures and analyze the structural conditions under which it emerges. Overall, our results suggest that shifting from continuous arithmetic weights to discrete Boolean lookups can provide a favorable accuracy-resilience trade-off for hardware fault tolerance.

Related papers

• LRX-PINN: A Layer-Resolving XNet Physics-Informed Neural Network with Integrated Cauchy Activations for Convection-Dominated Problems [7.72118589117645]
  Layer-Resolving XNet Physics-Informed Neural Network (LRX-PINN) based on integrated Cauchy activations.<n>We show that this structure matches the scaling of convection-dominated layers, inherits the Cauchy approximation mechanism at the derivative-profile level, and identifies (d/|w|) as the effective physical width of a ridge neuron.<n> Numerical experiments on several convection-dominated benchmarks show that LRX-PINN achieves higher accuracy than PIKAN and Fourier-feature PINNs while using less than (30%) of their trainable parameters.
  arXiv  Detail & Related papers  (2026-07-04T03:25:05Z)
• Deterministic Mapping of Topological Phases via Autoregressive Exogenous Neural Networks [0.0]
  Three dynamic neural network (NN) architectures -- NAR, NARX, and NIO -- are evaluated.<n>We show that NARX achieves superior predictive fidelity, reaching a Mean Squared Error (MSE) of $10-27$.<n>We observe a "complexity paradox" where the NARX model's accuracy collapses at higher delays.
  arXiv  Detail & Related papers  (2026-05-26T17:11:22Z)
• Prior-Informed Neural Network Initialization: A Spectral Approach for Function Parameterizing Architectures [3.0098885383612104]
  We propose a prior-informed design strategy that leverages the intrinsic spectral and temporal structure of the data.<n>A principled methodology is introduced that uses the Fast Fourier Transform to extract dominant seasonal priors.<n>Experiments on synthetic and real-world benchmarks demonstrate that embedding data-driven priors significantly accelerates convergence.
  arXiv  Detail & Related papers  (2026-03-17T11:08:52Z)
• A Neural Network for the Identical Kuramoto Equation: Architectural Considerations and Performance Evaluation [0.0]
  We investigate the efficiency of Deep Neural Networks (DNNs) to approximate the solution of a nonlocal conservation law derived from the identical-oscillator Kuramoto model.<n>Through systematic experimentation, we demonstrate that network configuration parameters influence convergence characteristics.<n>We identify fundamental limitations of standard feed-forward architectures when handling singular or piecewise-constant solutions.
  arXiv  Detail & Related papers  (2025-09-17T19:37:01Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• On the ISS Property of the Gradient Flow for Single Hidden-Layer Neural Networks with Linear Activations [0.0]
  We investigate the effects of overfitting on the robustness of gradient-descent training when subject to uncertainty on the gradient estimation. We show that the general overparametrized formulation introduces a set of spurious equilibria which lay outside the set where the loss function is minimized.
  arXiv  Detail & Related papers  (2023-05-17T02:26:34Z)
• Neuro-symbolic model for cantilever beams damage detection [0.0]
  We propose a neuro-symbolic model for the detection of damages in cantilever beams based on a novel cognitive architecture. The hybrid discriminative model is introduced under the name Logic Convolutional Neural Regressor.
  arXiv  Detail & Related papers  (2023-05-04T13:12:39Z)
• Robust lEarned Shrinkage-Thresholding (REST): Robust unrolling for sparse recover [87.28082715343896]
  We consider deep neural networks for solving inverse problems that are robust to forward model mis-specifications. We design a new robust deep neural network architecture by applying algorithm unfolding techniques to a robust version of the underlying recovery problem. The proposed REST network is shown to outperform state-of-the-art model-based and data-driven algorithms in both compressive sensing and radar imaging problems.
  arXiv  Detail & Related papers  (2021-10-20T06:15:45Z)
• Non-Singular Adversarial Robustness of Neural Networks [58.731070632586594]
  Adrial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. We formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
  arXiv  Detail & Related papers  (2021-02-23T20:59:30Z)
• Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
  Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
  arXiv  Detail & Related papers  (2020-11-18T18:52:08Z)
• Relaxing the Constraints on Predictive Coding Models [62.997667081978825]
  Predictive coding is an influential theory of cortical function which posits that the principal computation the brain performs is the minimization of prediction errors. Standard implementations of the algorithm still involve potentially neurally implausible features such as identical forward and backward weights, backward nonlinear derivatives, and 1-1 error unit connectivity. In this paper, we show that these features are not integral to the algorithm and can be removed either directly or through learning additional sets of parameters with Hebbian update rules without noticeable harm to learning performance.
  arXiv  Detail & Related papers  (2020-10-02T15:21:37Z)

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.