中文
相关论文

相关论文: FlatENN: Train Flat for Enhanced Fault Tolerance o…

200 篇论文

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing…

神经与进化计算 · 计算机科学 2016-09-23 Itay Hubara , Matthieu Courbariaux , Daniel Soudry , Ran El-Yaniv , Yoshua Bengio

Efficient time series forecasting has become critical for real-world applications, particularly with deep neural networks (DNNs). Efficiency in DNNs can be achieved through sparse connectivity and reducing the model size. However, finding…

机器学习 · 计算机科学 2024-06-13 Zahra Atashgahi , Mykola Pechenizkiy , Raymond Veldhuis , Decebal Constantin Mocanu

Quantized deep neural networks (QDNNs) are necessary for low-power, high throughput, and embedded applications. Previous studies mostly focused on developing optimization methods for the quantization of given models. However, quantization…

机器学习 · 计算机科学 2020-06-02 Yoonho Boo , Sungho Shin , Wonyong Sung

The rise of Deep Neural Networks (DNNs) has led to an increase in model size and complexity, straining the memory capacity of GPUs. Sparsity in DNNs, characterized as structural or ephemeral, has gained attention as a solution. This work…

机器学习 · 计算机科学 2023-11-30 Daniel Barley , Holger Fröning

The deployment of deep neural networks (DNNs) on resource-constrained edge devices such as field-programmable gate arrays (FPGAs) requires a careful balance of latency, power, and resource usage while maintaining high accuracy. Existing…

硬件体系结构 · 计算机科学 2025-03-18 Binglei Lou , Ruilin Wu , Philip Leong

Adversarial attacks have exposed serious vulnerabilities in Deep Neural Networks (DNNs) through their ability to force misclassifications through human-imperceptible perturbations to DNN inputs. We explore a new direction in the field of…

机器学习 · 计算机科学 2020-09-16 Sarada Krithivasan , Sanchari Sen , Anand Raghunathan

Spiking neural networks (SNNs) offer inherent energy efficiency due to their event-driven computation model, making them promising for edge AI deployment. However, their practical adoption is limited by the computational overhead of deep…

机器学习 · 计算机科学 2026-03-17 Parth Patne , Mahdi Taheri , Ali Mahani , Maksim Jenihhin , Reza Mahani , Christian Herglotz

The complexity of deep neural network algorithms for hardware implementation can be much lowered by optimizing the word-length of weights and signals. Direct quantization of floating-point weights, however, does not show good performance…

机器学习 · 计算机科学 2016-01-08 Wonyong Sung , Sungho Shin , Kyuyeon Hwang

Recurrent Neural Networks (RNNs) are used in state-of-the-art models in domains such as speech recognition, machine translation, and language modelling. Sparsity is a technique to reduce compute and memory requirements of deep learning…

机器学习 · 计算机科学 2017-11-09 Sharan Narang , Eric Undersander , Gregory Diamos

Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such systems remains a challenge due to the limited resources…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Yonggan Fu , Haoran You , Yang Zhao , Yue Wang , Chaojian Li , Kailash Gopalakrishnan , Zhangyang Wang , Yingyan Celine Lin

Low-precision representation of deep neural networks (DNNs) is critical for efficient deployment of deep learning application on embedded platforms, however, converting the network to low precision degrades its performance. Crucially,…

机器学习 · 计算机科学 2019-06-10 Alexander Finkelstein , Uri Almog , Mark Grobman

The biggest challenge for the deployment of Deep Neural Networks (DNNs) close to the generated data on edge devices is their size, i.e., memory footprint and computational complexity. Both are significantly reduced with quantization. With…

机器学习 · 计算机科学 2022-10-17 Cecilia Latotzke , Batuhan Balim , Tobias Gemmeke

The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…

机器学习 · 计算机科学 2023-09-01 Clemens JS Schaefer , Siddharth Joshi , Shan Li , Raul Blazquez

Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications. Due to their large sizes, however, compressiontechniques such as weight…

计算机视觉与模式识别 · 计算机科学 2021-10-15 Wentao Chen , Hailong Qiu , Jian Zhuang , Chutong Zhang , Yu Hu , Qing Lu , Tianchen Wang , Yiyu Shi , Meiping Huang , Xiaowe Xu

Bit-level sparsity in quantized deep neural networks (DNNs) offers significant potential for optimizing Multiply-Accumulate (MAC) operations. However, two key challenges still limit its practical exploitation. First, conventional bit-serial…

硬件体系结构 · 计算机科学 2025-07-15 Feilong Qiaoyuan , Jihe Wang , Zhiyu Sun , Linying Wu , Yuanhua Xiao , Danghui Wang

Most real-world applications that employ deep neural networks (DNNs) quantize them to low precision to reduce the compute needs. We present a method to improve the robustness of quantized DNNs to white-box adversarial attacks. We first…

计算机视觉与模式识别 · 计算机科学 2023-12-04 Saurabh Farkya , Aswin Raghavan , Avi Ziskind

Deep neural networks (DNNs) have enabled smart applications on hardware devices. However, these hardware devices are vulnerable to unintended faults caused by aging, temperature variance, and write errors. These faults can cause bit-flips…

机器学习 · 计算机科学 2024-12-02 Ninnart Fuengfusin , Hakaru Tamukoh

Activation sparsity improves compute efficiency and resource utilization in sparsity-aware neural network accelerators. As the predominant operation in DNNs is multiply-accumulate (MAC) of activations with weights to compute inner products,…

计算机视觉与模式识别 · 计算机科学 2021-07-16 Amirreza Yousefzadeh , Manolis Sifalakis

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

FPGAs have been shown to be a promising platform for deploying Quantised Neural Networks (QNNs) with high-speed, low-latency, and energy-efficient inference. However, the complexity of modern deep-learning models limits the performance on…

硬件体系结构 · 计算机科学 2025-11-06 Changhong Li , Biswajit Basu , Shreejith Shanker