RTNinja: a generalized machine learning framework for analyzing random telegraph noise signals in nanoelectronic devices

2025-07-11

AI Summary

Random telegraph noise (RTN), arising from stochastic carrier trapping/detrapping at defect states in nanoscale devices, induces performance degradation and reliability loss. Existing analytical methods rely on strong assumptions or manual intervention, limiting their applicability to high-noise, multi-source mixed signals. This work proposes the first fully automated, unsupervised machine learning framework for RTN analysis, integrating Bayesian model selection, probabilistic clustering, and optimization algorithms to jointly infer the number of noise sources, their amplitudes, and switching dynamics—without prior knowledge. A large-scale labeled dataset is generated via Monte Carlo simulation, and the framework is validated on 7,000 synthetic signals spanning diverse signal-to-noise ratios and complexity levels. It achieves high-fidelity signal deconvolution and source reconstruction, significantly outperforming conventional methods in accuracy. The framework is device-agnostic and highly scalable, establishing a general, robust paradigm for RTN characterization.

Technology Category

• Machine Learning: Probabilistic Circuits and Graphical Models
• Reasoning under Uncertainty: Stochastic Optimization
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Random telegraph noise is a prevalent variability phenomenon in nanoelectronic devices, arising from stochastic carrier exchange at defect sites and critically impacting device reliability and performance. Conventional analysis techniques often rely on restrictive assumptions or manual interventions, limiting their applicability to complex, noisy datasets. Here, we introduce RTNinja, a generalized, fully automated machine learning framework for the unsupervised analysis of random telegraph noise signals. RTNinja deconvolves complex signals to identify the number and characteristics of hidden individual sources, without requiring prior knowledge of the system. The framework comprises two modular components: LevelsExtractor, which uses Bayesian inference and model selection to denoise and discretize the signal; and SourcesMapper, which infers source configurations through probabilistic clustering and optimization. To evaluate performance, we developed a Monte Carlo simulator that generates labeled datasets spanning broad signal-to-noise ratios and source complexities; across 7000 such datasets, RTNinja consistently demonstrated high-fidelity signal reconstruction and accurate extraction of source amplitudes and activity patterns. Our results demonstrate that RTNinja offers a robust, scalable, and device-agnostic tool for random telegraph noise characterization, enabling large-scale statistical benchmarking, reliability-centric technology qualification, predictive failure modeling, and device physics exploration in next-generation nanoelectronics.

Problem

• Automated analysis of random telegraph noise in nanoelectronics
• Overcoming limitations of manual and assumption-based methods
• Identifying hidden noise sources without prior system knowledge

Innovation

• Automated unsupervised machine learning framework
• Bayesian inference for signal denoising and discretization
• Probabilistic clustering for source configuration inference