paper-with-me

홈 › Papers

Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation

2025-08-27 · Vojtech Mrazek, Konstantinos Balaskas, Paula Carolina Lozano Duarte, Zdenek Vasicek, Mehdi B. Tahoori, Georgios Zervakis arxiv

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.

📄 PDF Abstract BibTeX arXiv:2508.19660

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Trained Ternary Quantization

2016-12-04 · Chenzhuo Zhu, Song Han, Huizi Mao, William J. Dally

Deep neural networks are widely used in machine learning applications. However, the deployment of large neural networks models can be difficult to deploy on mobile devices with limited power budgets. To solve this proble…

Quantization

Hyperspherical Loss-Aware Ternary Quantization

2022-12-24 · Dan Liu, Xue Liu

Most of the existing works use projection functions for ternary quantization in discrete space. Scaling factors and thresholds are used in some cases to improve the model accuracy. However, the gradients used for optimiz…

image-classificationImage Classificationobject-detectionObject Detection+1

Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML

2020-03-11 · Giuseppe Di Guglielmo, Javier Duarte, Philip Harris, Duc Hoang 외

We present the implementation of binary and ternary neural networks in the hls4ml library, designed to automatically convert deep neural network models to digital circuits with FPGA firmware. Starting from benchmark mode…

Handwritten Digit Recognition

TiM-DNN: Ternary in-Memory accelerator for Deep Neural Networks

2019-09-15 · Shubham Jain, Sumeet Kumar Gupta, Anand Raghunathan

The use of lower precision has emerged as a popular technique to optimize the compute and storage requirements of complex Deep Neural Networks (DNNs). In the quest for lower precision, recent studies have shown that tern…

GPUImage ClassificationLanguage Modelling

FATNN: Fast and Accurate Ternary Neural Networks

2020-08-12 · ICCV 2021 10 · Peng Chen, Bohan Zhuang, Chunhua Shen

Ternary Neural Networks (TNNs) have received much attention due to being potentially orders of magnitude faster in inference, as well as more power efficient, than full-precision counterparts. However, 2 bits are require…

image-classificationImage ClassificationQuantization