On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks

• URL: http://arxiv.org/abs/2605.24649v1
• Date: Sat, 23 May 2026 16:30:00 GMT
• Title: On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks
• Abstract summary: Recurrent Neural Networks (RNNs) can learn to predict Signal Temporal Logic (STL) verdicts online from partial trajectories.<n>Standard RNN architectures offer no structural guarantee that outputs degrade gracefully under sensor degradation.<n>We introduce the Recurrent Differentiable Ternary Logic Gate Network (R-DTLGN), a recurrent architecture that operates over Kleene's three-valued logic $-1, 0, +1$.
• Score: 4.91491092996493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recurrent Neural Networks (RNNs) can learn to predict Signal Temporal Logic (STL) verdicts online from partial trajectories, but deploying them as runtime monitors in safety-critical systems demands more than predictive accuracy. Standard RNN architectures offer no structural guarantee that outputs degrade gracefully under sensor degradation; a dropped input can silently flip a verdict from safe to unsafe. We introduce the Recurrent Differentiable Ternary Logic Gate Network (R-DTLGN), a recurrent architecture that operates over Kleene's three-valued logic $\{-1, 0, +1\}$, where $0$ explicitly represents unknown. The R-DTLGN trains through continuous polynomial surrogates and hardens to a discrete ternary logic circuit at inference. We analyze the hardened circuit through two gate vocabularies derived from two orderings on the ternary domain: numerically monotone gates ensure stable recurrent dynamics, while information-monotone gates, when present, guarantee principled abstention (unknown inputs never produce wrong outputs) and monotonicity in input certainty (more information can only improve the verdict). We show that the recurrent connections required by bounded STL operators use exclusively AND and OR, which belong to both vocabularies, linking the monitoring task to the architecture's guarantees. A realizability bound derived from the STL formula's temporal operators directly sizes the network's hidden state, replacing hyperparameter search with a formula-driven specification. We evaluate on STL specifications over D4RL PointMaze navigation data, testing prediction accuracy, degradation under predicate dropout, and the accuracy-versus-safety tradeoff between two label construction pipelines. The R-DTLGN is, to our knowledge, the first recurrent architecture that couples learned temporal prediction with formal degradation guarantees rooted in three-valued logic.

Related papers

• EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHE [0.0]
  We present EI-DDLGN, the first in-depth study of TFHE-based DDLGN inference.<n>We also introduce Model-Fixed-Wire PBS Bypass, a semantics-preserving execution strategy.<n> Evaluations across 72 depth-width configurations on MNIST, FashionMNIST, and UCI Phishing show that DDLGNs constitute an efficient alternative to arithmetic TFHE inference.
  arXiv  Detail & Related papers  (2026-09-12T01:00:19Z)
• On the Depth Scalability of Logic Gate Networks [8.615180964202992]
  We introduce Input-Anchored Logic Gate Networks (IALGNs)<n>We show that IALGNs achieve consistent fixed-width depth--accuracy improvements beyond 100 layers.<n>These results demonstrate that scalable depth in LGNs requires both stable optimization and an information-access pattern.
  arXiv  Detail & Related papers  (2026-07-19T20:11:53Z)
• Dualformer: Efficient Feature Extractor for Complex-valued Blind Communication Signal Analysis [20.436783567450206]
  We propose dual-channel neural network (DualNN) that efficiently exploits complex-valued signals through parameter sharing across IQ channels.<n>Unlike traditional real-valued or complex-valued models, DualNN is a groundbreaking framework which shares the network parameters for processing the real and imaginary parts of the complex-valued signals.
  arXiv  Detail & Related papers  (2026-06-30T08:49:01Z)
• How LLMs Fail and Generalize in RTL Coding for Hardware Design? [56.361436215029045]
  We introduce a new error taxonomy grounded in problem solvability, inspired by cognitive theory.<n>Our taxonomy categorizes failures into syntactic, semantic, solvable functional, and unsolvable functional types.
  arXiv  Detail & Related papers  (2026-04-26T14:34:49Z)
• Ternary Logic Encodings of Temporal Behavior Trees with Application to Control Synthesis [5.99447754429793]
  Temporal BTs offer a promising approach by leveraging existing temporal logic formalisms to specify and verify executions of BTs.<n>We reformulate TBTs using a ternary-valued Signal Temporal Logic (STL) amenable for control.<n>We propose mixed-integer linear encodings for partial trajectory STL and TBTs over ternary logic allowing for correct-by-construction control strategies.
  arXiv  Detail & Related papers  (2026-04-13T22:07:05Z)
• Polynomial Surrogate Training for Differentiable Ternary Logic Gate Networks [3.2249474972573555]
  We introduce Polynomial Surrogate Training (PST), which represents each ternary neuron as a degree-$ (2,2)$ with 9 learnable coefficients.<n>PST trains $2$-$3times$ faster than binary DLGNs and discover true ternary gates that are functionally diverse.
  arXiv  Detail & Related papers  (2026-02-27T20:37:17Z)
• TorchLean: Formalizing Neural Networks in Lean [71.68907600404513]
  We introduce TorchLean, a framework that treats learned models as first-class mathematical objects with a single, precise semantics shared by execution and verification.<n>We validate TorchLean end-to-end on certified robustness, physics-informed residual bounds for PINNs, and Lyapunov-style neural controller verification.
  arXiv  Detail & Related papers  (2026-02-26T05:11:44Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs [50.075587392477935]
  We conduct the first large-scale empirical study of 705 real-world failures from the open-source DeepSeek, Llama, and Qwen ecosystems.<n>Our analysis reveals a paradigm shift: white-box orchestration relocates the reliability bottleneck from model algorithmic defects to the systemic fragility of the deployment stack.
  arXiv  Detail & Related papers  (2026-01-20T06:42:56Z)
• ReGAIN: Retrieval-Grounded AI Framework for Network Traffic Analysis [5.887997322139195]
  ReGAIN is a framework that combines traffic summarization, retrieval-augmented generation (RAG), and Large Language Model (LLM) reasoning for transparent and accurate network traffic analysis.<n> evaluated on ICMP ping flood and TCP SYN flood traces from the real-world traffic dataset.
  arXiv  Detail & Related papers  (2025-12-23T00:16:14Z)
• Learning from Scratch: Structurally-masked Transformer for Next Generation Lib-free Simulation [5.564681128355971]
  This paper proposes a neural framework for power and timing prediction of multi-stage data path.<n>To the best of our knowledge, this is the first language-based, netlist-aware neural network designed explicitly for standard cells.
  arXiv  Detail & Related papers  (2025-07-23T10:46:25Z)
• Logical blocks for fault-tolerant topological quantum computation [55.41644538483948]
  We present a framework for universal fault-tolerant logic motivated by the need for platform-independent logical gate definitions. We explore novel schemes for universal logic that improve resource overheads. Motivated by the favorable logical error rates for boundaryless computation, we introduce a novel computational scheme.
  arXiv  Detail & Related papers  (2021-12-22T19:00:03Z)
• Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units [68.30422112784355]
  We propose a new gating mechanism within general gated recurrent neural networks to handle this issue. The proposed gates directly short connect the extracted input features to the outputs of vanilla gates. We verify the proposed gating mechanism on three popular types of gated RNNs including LSTM, GRU and MGU.
  arXiv  Detail & Related papers  (2020-02-26T07:51:38Z)

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.