English
Related papers

Related papers: SQUAT: Stateful Quantization-Aware Training in Rec…

200 papers

Spiking Neural Networks (SNNs) are highly energy-efficient during inference, making them particularly suitable for deployment on neuromorphic hardware. Their ability to process event-driven inputs, such as data from dynamic vision sensors…

Machine Learning · Computer Science 2025-04-10 Sirine Arfa , Bernhard Vogginger , Chen Liu , Johannes Partzsch , Mark Schone , Christian Mayr

Neuromorphic and quantum computing have recently emerged as promising paradigms for advancing artificial intelligence, each offering complementary strengths. Neuromorphic systems built on spiking neurons excel at processing time series data…

Neural and Evolutionary Computing · Computer Science 2026-02-25 Jiechen Chen , Bipin Rajendran , Osvaldo Simeone

Spiking Neural Networks (SNNs) have been widely praised for their high energy efficiency and immense potential. However, comprehensive research that critically contrasts and correlates SNNs with quantized Artificial Neural Networks (ANNs)…

Neural and Evolutionary Computing · Computer Science 2023-11-21 Guobin Shen , Dongcheng Zhao , Tenglong Li , Jindong Li , Yi Zeng

Quantized Neural Networks (QNNs) are often used to improve network efficiency during the inference phase, i.e. after the network has been trained. Extensive research in the field suggests many different quantization schemes. Still, the…

Machine Learning · Computer Science 2018-06-19 Ron Banner , Itay Hubara , Elad Hoffer , Daniel Soudry

This paper presents incremental network quantization (INQ), a novel method, targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version whose weights are constrained…

Computer Vision and Pattern Recognition · Computer Science 2017-08-28 Aojun Zhou , Anbang Yao , Yiwen Guo , Lin Xu , Yurong Chen

Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) represent two mainstream model quantization approaches. However, PTQ often leads to unacceptable performance degradation in quantized models, while QAT imposes…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Xinhao Wang , Zhiwei Lin , Zhongyu Xia , Yongtao Wang

Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead to large quantization errors when…

Spiking neural networks (SNNs) support energy-efficient machine intelligence because event-driven computation and sparse activity map naturally to low-power digital hardware. In practical implementations, however, membrane states, synaptic…

Neural and Evolutionary Computing · Computer Science 2026-04-02 Lei Zhang

Spiking Neural Networks (SNNs) promise higher energy efficiency over conventional Quantized Artificial Neural Networks (QNNs) due to their event-driven, spike-based computation. However, prevailing energy evaluations often oversimplify,…

Neural and Evolutionary Computing · Computer Science 2026-05-13 Zhanglu Yan , Zhenyu Bai , Weng-Fai Wong

Quantization is a natural complement to the sparse, event-driven computation of Spiking Neural Networks, reducing memory bandwidth and arithmetic cost for deployment on resource-constrained hardware. However, existing SNN quantization…

Machine Learning · Computer Science 2026-04-17 Evan Gibson Smith , Jacob Whitehill , Fatemeh Ganji

With the rapid increase in the size of neural networks, model compression has become an important area of research. Quantization is an effective technique at decreasing the model size, memory access, and compute load of large models.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-26 David Qiu , David Rim , Shaojin Ding , Oleg Rybakov , Yanzhang He

Deep neural networks (DNNs) are quantized for efficient inference on resource-constrained platforms. However, training deep learning models with low-precision weights and activations involves a demanding optimization task, which calls for…

Machine Learning · Computer Science 2021-05-25 Ziang Long , Penghang Yin , Jack Xin

We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bits of precision…

Machine Learning · Computer Science 2018-06-22 Raghuraman Krishnamoorthi

Deep Neural Networks (DNNs) have gained immense success in cognitive applications and greatly pushed today's artificial intelligence forward. The biggest challenge in executing DNNs is their extremely data-extensive computations. The…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Fuqiang Liu , C. Liu

Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints, yet achieving stable and robust optimization at ultra-low bitwidths remains challenging. Common approaches based on the…

Machine Learning · Computer Science 2026-02-19 Tianyi Chen , Sihan Chen , Xiaoyi Qu , Dan Zhao , Ruomei Yan , Jongwoo Ko , Luming Liang , Pashmina Cameron

The post-training quantization (PTQ) challenge of bringing quantized neural net accuracy close to original has drawn much attention driven by industry demand. Many of the methods emphasize optimization of a specific degree-of-freedom (DoF),…

Machine Learning · Statistics 2023-03-21 Alex Finkelstein , Ella Fuchs , Idan Tal , Mark Grobman , Niv Vosco , Eldad Meller

Spiking neural networks are efficient computation models for low-power environments. Spike-based BP algorithms and ANN-to-SNN (ANN2SNN) conversions are successful techniques for SNN training. Nevertheless, the spike-base BP training is slow…

Neural and Evolutionary Computing · Computer Science 2023-08-31 Jianxiong Tang , Jianhuang Lai , Xiaohua Xie , Lingxiao Yang , Wei-Shi Zheng

Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is its slow convergence and early performance plateau,…

Low-bit deep neural networks (DNNs) become critical for embedded applications due to their low storage requirement and computing efficiency. However, they suffer much from the non-negligible accuracy drop. This paper proposes the stochastic…

Computer Vision and Pattern Recognition · Computer Science 2017-08-04 Yinpeng Dong , Renkun Ni , Jianguo Li , Yurong Chen , Jun Zhu , Hang Su

Quantization has become a predominant approach for model compression, enabling deployment of large models trained on GPUs onto smaller form-factor devices for inference. Quantization-aware training (QAT) optimizes model parameters with…

Machine Learning · Computer Science 2022-12-13 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell