Compact Yet Highly Accurate Printed Classifiers Using Sequential Support Vector Machine Circuits

2025-02-03

AI Summary

To address the challenge of balancing accuracy and complexity in machine learning models under stringent area and power constraints of printed electronics, this paper proposes a lightweight, application-specific classifier tailored for printing fabrication. The core innovation is the first hardware implementation of a sequential support vector machine (SVM) architecture, integrating customized control/storage units with a single multiply-accumulate (MAC) engine to enable algorithm-hardware co-optimization. Key techniques include on-chip state reuse, low-overhead MAC design, and hardware-aware SVM mapping, collectively minimizing silicon footprint. Compared to the state-of-the-art printed ML solutions, the proposed design achieves a 6× reduction in average chip area, a 4.6% improvement in classification accuracy, and significant gains in the joint energy-efficiency–accuracy metric. This work establishes a new paradigm for high-accuracy, ultra-compact ML deployment in resource-constrained printed intelligent devices.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Human-in-the-loop Machine Learning
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Printed Electronics (PE) technology has emerged as a promising alternative to silicon-based computing. It offers attractive properties such as on-demand ultra-low-cost fabrication, mechanical flexibility, and conformality. However, PE are governed by large feature sizes, prohibiting the realization of complex printed Machine Learning (ML) classifiers. Leveraging PE's ultra-low non-recurring engineering and fabrication costs, designers can fully customize hardware to a specific ML model and dataset, significantly reducing circuit complexity. Despite significant advancements, state-of-the-art solutions achieve area efficiency at the expense of considerable accuracy loss. Our work mitigates this by designing area- and power-efficient printed ML classifiers with little to no accuracy degradation. Specifically, we introduce the first sequential Support Vector Machine (SVM) classifiers, exploiting the hardware efficiency of bespoke control and storage units and a single Multiply-Accumulate compute engine. Our SVMs yield on average 6x lower area and 4.6% higher accuracy compared to the printed state of the art.

Problem

• Printed Electronics
• Machine Learning Models
• Accuracy and Power Efficiency

Innovation

• Sequential Support Vector Machine
• Space Efficiency
• Accuracy Improvement