Multi-objective Bayesian Optimization with Human-in-the-Loop for Flexible Neuromorphic Electronics Fabrication

2025-10-08

AI Summary

Fabricating flexible neuromorphic electronics faces challenges of interfacial incompatibility between metal oxides and polymers, coupled with difficulties in multi-parameter optimization of photopolymerization. Method: This work proposes a human-in-the-loop multi-objective Bayesian optimization framework, integrating a solution-processed aluminum oxide dielectric layer fabricated via photonic annealing. The framework dynamically incorporates expert feedback and failure data into surrogate model updates, and employs Pareto frontier analysis alongside Shapley value interpretation to identify critical process parameters. Contribution/Results: Compared to conventional grid search, the method drastically reduces experimental iterations and successfully identifies Pareto-optimal solutions balancing low leakage current and minimal capacitance dispersion. It demonstrates robustness and transferability, establishing a new paradigm for multi-objective, high-failure-rate materials process optimization.

Technology Category

• Machine Learning: Optimization
• Search and Optimization: Algorithm Configuration
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Neuromorphic computing hardware enables edge computing and can be implemented in flexible electronics for novel applications. Metal oxide materials are promising candidates for fabricating flexible neuromorphic electronics, but suffer from processing constraints due to the incompatibilities between oxides and polymer substrates. In this work, we use photonic curing to fabricate flexible metal-insulator-metal capacitors with solution-processible aluminum oxide dielectric tailored for neuromorphic applications. Because photonic curing outcomes depend on many input parameters, identifying an optimal processing condition through a traditional grid-search approach is unfeasible. Here, we apply multi-objective Bayesian optimization (MOBO) to determine photonic curing conditions that optimize the trade-off between desired electrical properties of large capacitance-frequency dispersion and low leakage current. Furthermore, we develop a human-in-the-loop (HITL) framework for incorporating failed experiments into the MOBO machine learning workflow, demonstrating that this framework accelerates optimization by reducing the number of experimental rounds required. Once optimization is concluded, we analyze different Pareto-optimal conditions to tune the dielectrics properties and provide insight into the importance of different inputs through Shapley Additive exPlanations analysis. The demonstrated framework of combining MOBO with HITL feedback can be adapted to a wide range of multi-objective experimental problems that have interconnected inputs and high experimental failure rates to generate usable results for machine learning models.

Problem

• Optimizing photonic curing parameters for flexible neuromorphic electronics
• Balancing capacitance-frequency dispersion with low leakage current
• Incorporating failed experiments into multi-objective Bayesian optimization workflow

Innovation

• Multi-objective Bayesian optimization for photonic curing parameters
• Human-in-the-loop framework incorporating failed experiments
• Shapley analysis to interpret multi-variable input importance