Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation
This work addresses the problem of enabling printed-battery-powered operation with minimal accuracy loss for applications requiring flexibility and low cost in printed electronics, representing a significant advancement rather than an incremental improvement.
The paper tackles the challenge of balancing classification accuracy and area efficiency in printed neural networks for printed electronics, proposing an automated framework for designing ternary neural networks with arbitrary input precision that achieves 17x area and 59x power improvements over existing approximate printed neural networks.
Printed electronics offer a promising alternative for applications beyond silicon-based systems, requiring properties like flexibility, stretchability, conformality, and ultra-low fabrication costs. Despite the large feature sizes in printed electronics, printed neural networks have attracted attention for meeting target application requirements, though realizing complex circuits remains challenging. This work bridges the gap between classification accuracy and area efficiency in printed neural networks, covering the entire processing-near-sensor system design and co-optimization from the analog-to-digital interface-a major area and power bottleneck-to the digital classifier. We propose an automated framework for designing printed Ternary Neural Networks with arbitrary input precision, utilizing multi-objective optimization and holistic approximation. Our circuits outperform existing approximate printed neural networks by 17x in area and 59x in power on average, being the first to enable printed-battery-powered operation with under 5% accuracy loss while accounting for analog-to-digital interfacing costs.