中文
相关论文

相关论文: Towards Fault-Tolerant Quantum Deep Learning: Desi…

200 篇论文

Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN computation and storage by decreasing the bitwidth of…

Fault-tolerant Quantum Processing Units (QPUs) promise to deliver exponential speed-ups in select computational tasks, yet their integration into modern deep learning pipelines remains unclear. In this work, we take a step towards bridging…

量子物理 · 物理学 2026-05-19 Arthur G. Rattew , Po-Wei Huang , Naixu Guo , Lirandë Pira , Patrick Rebentrost

Quantum computing is a new computational paradigm that promises applications in several fields, including machine learning. In the last decade, deep learning, and in particular Convolutional neural networks (CNN), have become essential for…

量子物理 · 物理学 2021-06-14 Iordanis Kerenidis , Jonas Landman , Anupam Prakash

The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increases in memory and computational demands make deep learning…

机器学习 · 计算机科学 2024-06-07 Daniel Becking , Maximilian Dreyer , Wojciech Samek , Karsten Müller , Sebastian Lapuschkin

Deep neural networks (DNNs) can be made hardware-efficient by reducing the numerical precision of the weights and activations of the network and by improving the network's resilience to noise. However, this gain in efficiency often comes at…

Large machine learning models based on Convolutional Neural Networks (CNNs) with rapidly increasing number of parameters, trained with massive amounts of data, are being deployed in a wide array of computer vision tasks from self-driving…

计算机视觉与模式识别 · 计算机科学 2021-10-14 Rishab Parthasarathy , Rohan Bhowmik

State-of-the-art deep neural networks are trained with large amounts (millions or even billions) of data. The expensive computation and memory costs make it difficult to train them on limited hardware resources, especially for recent…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Daquan Zhou , Kai Wang , Jianyang Gu , Xiangyu Peng , Dongze Lian , Yifan Zhang , Yang You , Jiashi Feng

We present a novel framework for applying deep neural networks (DNN) to soft decoding of linear codes at arbitrary block lengths. Unlike other approaches, our framework allows unconstrained DNN design, enabling the free application of…

信息论 · 计算机科学 2018-02-27 Amir Bennatan , Yoni Choukroun , Pavel Kisilev

Neural networks enjoy widespread success in both research and industry and, with the imminent advent of quantum technology, it is now a crucial challenge to design quantum neural networks for fully quantum learning tasks. Here we propose…

In this paper, we present a novel framework for enhancing the performance of Quanvolutional Neural Networks (QuNNs) by introducing trainable quanvolutional layers and addressing the critical challenges associated with them. Traditional…

机器学习 · 计算机科学 2025-07-18 Muhammad Kashif , Muhammad Shafique

In the realm of computational science and engineering, constructing models that reflect real-world phenomena requires solving partial differential equations (PDEs) with different conditions. Recent advancements in neural operators, such as…

量子物理 · 物理学 2025-06-11 Pengpeng Xiao , Muqing Zheng , Anran Jiao , Xiu Yang , Lu Lu

Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and inference more computationally challenging. In an attempt to…

机器学习 · 统计学 2024-03-04 Lingyu Gu , Yongqi Du , Yuan Zhang , Di Xie , Shiliang Pu , Robert C. Qiu , Zhenyu Liao

The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic,…

This work proposes a unified three-stage framework that produces a quantized DNN with balanced fault and attack robustness. The first stage improves attack resilience via fine-tuning that desensitizes feature representations to small input…

Running Deep Neural Network (DNN) models on devices with limited computational capability is a challenge due to large compute and memory requirements. Quantized Neural Networks (QNNs) have emerged as a potential solution to this problem,…

计算机视觉与模式识别 · 计算机科学 2018-05-31 Yaman Umuroglu , Magnus Jahre

Current Deep Learning approaches have been very successful using convolutional neural networks (CNN) trained on large graphical processing units (GPU)-based computers. Three limitations of this approach are: 1) they are based on a simple…

Quantization of deep neural networks (DNN) has been proven effective for compressing and accelerating DNN models. Data-free quantization (DFQ) is a promising approach without the original datasets under privacy-sensitive and confidential…

机器学习 · 计算机科学 2022-02-16 Cong Guo , Yuxian Qiu , Jingwen Leng , Xiaotian Gao , Chen Zhang , Yunxin Liu , Fan Yang , Yuhao Zhu , Minyi Guo

Deep neural network (DNN) quantization converting floating-point (FP) data in the network to integers (INT) is an effective way to shrink the model size for memory saving and simplify the operations for compute acceleration. Recently,…

机器学习 · 计算机科学 2020-01-01 Yukuan Yang , Shuang Wu , Lei Deng , Tianyi Yan , Yuan Xie , Guoqi Li

This paper presents a unified framework for codifying and automating optimization strategies to efficiently deploy deep neural networks (DNNs) on resource-constrained hardware, such as FPGAs, while maintaining high performance, accuracy,…

硬件体系结构 · 计算机科学 2026-02-11 Zhiqiang Que , Jose G. F. Coutinho , Ce Guo , Hongxiang Fan , Wayne Luk

In recent years Deep Neural Networks (DNNs) have been rapidly developed in various applications, together with increasingly complex architectures. The performance gain of these DNNs generally comes with high computational costs and large…

机器学习 · 计算机科学 2017-12-05 Yiren Zhou , Seyed-Mohsen Moosavi-Dezfooli , Ngai-Man Cheung , Pascal Frossard
‹ 上一页 1 2 3 10 下一页 ›