Determinism in the Undetermined: Deterministic Output in Charge-Conserving Continuous-Time Neuromorphic Systems with Temporal Stochasticity

2026-03-16 · Jing Yan, Kang You, Zhezhi He, Yaoyu Zhang arxiv

Achieving deterministic computation results in asynchronous neuromorphic systems remains a fundamental challenge due to the inherent temporal stochasticity of continuous-time hardware. To address this, we develop a unified continuous-time framework for spiking neural networks (SNNs) that couples the Law of Charge Conservation with minimal neuron-level constraints. This integration ensures that the terminal state depends solely on the aggregate input charge, providing a unique cumulated output invariant to temporal stochasticity. We prove that this mapping is strictly invariant to spike timing in acyclic networks, whereas recurrent connectivity can introduce temporal sensitivity. Furthermore, we establish an exact representational correspondence between these charge-conserving SNNs and quantized artificial neural networks, bridging the gap between static deep learning and event-driven dynamics without approximation errors. These results establish a rigorous theoretical basis for designing continuous-time neuromorphic systems that harness the efficiency of asynchronous processing while maintaining algorithmic determinism.

📄 PDF Abstract BibTeX arXiv:2603.15987

Code (0)

등록된 구현이 없습니다.

Non-Determinism of "Deterministic" LLM Settings

2024-08-06 · Berk Atıl, Sarp Aykent, Alexa Chittams, Lisheng Fu 외

LLM (large language model) practitioners commonly notice that outputs can vary for the same inputs under settings expected to be deterministic. Yet the questions of how pervasive this is, and with what impact on results,…

Language Modeling Language Modelling Large Language Model

On the Foundations of Trustworthy Artificial Intelligence

2026-03-26 · TJ Dunham arxiv

We prove that platform-deterministic inference is necessary and sufficient for trustworthy AI. We formalize this as the Determinism Thesis and introduce trust entropy to quantify the cost of non-determinism, proving that…

Deterministic Implementations for Reproducibility in Deep Reinforcement Learning

2018-09-15 · Prabhat Nagarajan, Garrett Warnell, Peter Stone

While deep reinforcement learning (DRL) has led to numerous successes in recent years, reproducing these successes can be extremely challenging. One reproducibility challenge particularly relevant to DRL is nondeterminis…

Deep Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+1

Overarching Computation Model (OCM)

2018-08-01 · Henok Ghebrechristos, Drew Miller

Existing models of computation, such as a Turing machine (hereafter, TM), do not consider the agent involved in interpreting the outcome of the computation. We argue that a TM, or any other computation model, has no sign…

model

LLM-42: Enabling Determinism in LLM Inference with Verified Speculation

2026-01-25 · Raja Gond, Aditya K Kamath, Ramachandran Ramjee, Ashish Panwar arxiv

In LLM inference, the same prompt may yield different outputs across different runs. At the system level, this non-determinism arises from floating-point non-associativity combined with dynamic batching and GPU kernels w…