# Cross-Layer Approximation For Printed Machine Learning Circuits

arXiv: https://arxiv.org/abs/2203.05915 · HTML: https://mlsanity.com/paper/2203.05915/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 19 references that are in the map.
- First posted on arXiv 11 Mar 2022.

## Builds on (most cited first, 1 of 1)

- [autoAx: An Automatic Design Space Exploration and Circuit Building Methodology utilizing Libraries of Approximate Components](https://mlsanity.com/paper/1902.10807/) (2019)

## Built on by (most cited first, 12 of 12)

- [Co-Design of Approximate Multilayer Perceptron for Ultra-Resource Constrained Printed Circuits](https://mlsanity.com/paper/2302.14576/) (2023)
- [Approximate Computing and the Efficient Machine Learning Expedition](https://mlsanity.com/paper/2210.00497/) (2022)
- [Model-to-Circuit Cross-Approximation For Printed Machine Learning Classifiers](https://mlsanity.com/paper/2303.08255/) (2023)
- [Bespoke Approximation of Multiplication-Accumulation and Activation Targeting Printed Multilayer Perceptrons](https://mlsanity.com/paper/2312.17612/) (2023)
- [Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications](https://mlsanity.com/paper/2307.11128/) (2023)
- [Embedding Hardware Approximations in Discrete Genetic-based Training for Printed MLPs](https://mlsanity.com/paper/2402.02930/) (2024)
- [Compact Yet Highly Accurate Printed Classifiers Using Sequential Support Vector Machine Circuits](https://mlsanity.com/paper/2502.01498/) (2025)
- [Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation](https://mlsanity.com/paper/2508.19660/) (2025)
- [Lifetime-Aware Design for Item-Level Intelligence at the Extreme Edge](https://mlsanity.com/paper/2509.08193/) (2025)
- [MaRVIn: A Cross-Layer Mixed-Precision RISC-V Framework for DNN Inference, from ISA Extension to Hardware Acceleration](https://mlsanity.com/paper/2509.15187/) (2025)
- [Hybrid unary-binary design for multiplier-less printed Machine Learning classifiers](https://mlsanity.com/paper/2509.15316/) (2025)
- [Bespoke Co-processor for Energy-Efficient Health Monitoring on RISC-V-based Flexible Wearables](https://mlsanity.com/paper/2511.05985/) (2025)

## Abstract (arXiv)

Printed electronics (PE) feature low non-recurring engineering costs and low per unit-area fabrication costs, enabling thus extremely low-cost and on-demand hardware. Such low-cost fabrication allows for high customization that would be infeasible in silicon, and bespoke architectures prevail to improve the efficiency of emerging PE machine learning (ML) applications. However, even with bespoke architectures, the large feature sizes in PE constraint the complexity of the ML models that can be implemented. In this work, we bring together, for the first time, approximate computing and PE design targeting to enable complex ML models, such as Multi-Layer Perceptrons (MLPs) and Support Vector Machines (SVMs), in PE. To this end, we propose and implement a cross-layer approximation, tailored for bespoke ML architectures. At the algorithmic level we apply a hardware-driven coefficient approximation of the ML model and at the circuit level we apply a netlist pruning through a full search exploration. In our extensive experimental evaluation we consider 14 MLPs and SVMs and evaluate more than 4300 approximate and exact designs. Our results demonstrate that our cross approximation delivers Pareto optimal designs that, compared to the state-of-the-art exact designs, feature 47% and 44% average area and power reduction, respectively, and less than 1% accuracy loss.