paper-with-me

홈 › Papers

WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic

2021-01-01 · ICLR 2021 1 · Renkun Ni, Hong-Min Chu, Oscar Castaneda, Ping-Yeh Chiang, Christoph Studer, Tom Goldstein

Low-precision neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity. Nonetheless, these products are accumulated using high-precision (typically 32-bit) additions, an operation that dominates the arithmetic complexity of inference when using extreme quantization (e.g., binary weights). To further optimize inference, we propose WrapNet that adapts neural networks to use low-precision (8-bit) additions in the accumulators, achieving classification accuracy comparable to their 32-bit counterparts. We achieve resilience to low-precision accumulation by inserting a cyclic activation layer, as well as an overflow penalty regularizer. We demonstrate the efficacy of our approach on both software and hardware platforms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic

2020-07-26 · Renkun Ni, Hong-Min Chu, Oscar Castañeda, Ping-Yeh Chiang 외

Low-resolution neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity. Nonetheless, these products are accumulated using high-resolution (typically 32-bit…

Quantization

Automatic Network Adaptation for Ultra-Low Uniform-Precision Quantization

2022-12-21 · Seongmin Park, Beomseok Kwon, Jieun Lim, Kyuyoung Sim 외

Uniform-precision neural network quantization has gained popularity since it simplifies densely packed arithmetic unit for high computing capability. However, it ignores heterogeneous sensitivity to the impact of quantiz…

Neural Architecture SearchQuantization

Gradient-based Automatic Mixed Precision Quantization for Neural Networks On-Chip

2024-05-01 · Chang Sun, Thea K. Årrestad, Vladimir Loncar, Jennifer Ngadiuba 외

Model size and inference speed at deployment time, are major challenges in many deep learning applications. A promising strategy to overcome these challenges is quantization. However, a straightforward uniform quantizati…

Jet TaggingQuantization

Low-Precision Floating-Point Schemes for Neural Network Training

2018-04-14 · Marc Ortiz, Adrián Cristal, Eduard Ayguadé, Marc Casas

The use of low-precision fixed-point arithmetic along with stochastic rounding has been proposed as a promising alternative to the commonly used 32-bit floating point arithmetic to enhance training neural networks traini…

Characterizing the Impact of NVFP4 Quantization for Low-Power Edge AI Deployment

2026-06-03 · Ovishake Sen, Venkata Nithin Kamineni, Daniel Lobo, Swarup Bhunia 외 arxiv

Energy-efficient neural-network inference at the edge requires reducing arithmetic cost, memory traffic, computation energy, and storage overhead while maintaining acceptable accuracy. This paper presents an ablation-foc…