中文
相关论文

相关论文: Binarized Neural Networks: Training Deep Neural Ne…

200 篇论文

Quantizing weights and activations of deep neural networks is essential for deploying them in resource-constrained devices, or cloud platforms for at-scale services. While binarization is a special case of quantization, this extreme case…

计算机视觉与模式识别 · 计算机科学 2021-04-02 Phuoc Pham , Jacob Abraham , Jaeyong Chung

Many available formal verification methods have been shown to be instances of a unified Branch-and-Bound (BaB) formulation. We propose a novel machine learning framework that can be used for designing an effective branching strategy as well…

机器学习 · 计算机科学 2021-07-28 Florian Jaeckle , Jingyue Lu , M. Pawan Kumar

Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of…

计算机视觉与模式识别 · 计算机科学 2018-07-27 Dongqing Zhang , Jiaolong Yang , Dongqiangzi Ye , Gang Hua

Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts. However, the accuracy gains are often based on specialized model designs using additional 32-bit…

机器学习 · 计算机科学 2021-06-15 Nianhui Guo , Joseph Bethge , Haojin Yang , Kai Zhong , Xuefei Ning , Christoph Meinel , Yu Wang

Binary Neural Networks~(BNNs) have been proven to be highly effective for deploying deep neural networks on mobile and embedded platforms. Most existing works focus on minimizing quantization errors, improving representation ability, or…

计算机视觉与模式识别 · 计算机科学 2024-07-09 Jingyang Xiang , Zuohui Chen , Siqi Li , Qing Wu , Yong Liu

Bayesian neural networks (BNNs) demonstrate promising success in improving the robustness and uncertainty quantification of modern deep learning. However, they generally struggle with underfitting at scale and parameter efficiency. On the…

Binary representation is desirable for its memory efficiency, computation speed and robustness. In this paper, we propose adjustable bounded rectifiers to learn binary representations for deep neural networks. While hard constraining…

机器学习 · 计算机科学 2015-11-20 Zhirong Wu , Dahua Lin , Xiaoou Tang

Quantization and pruning are core techniques used to reduce the inference costs of deep neural networks. State-of-the-art quantization techniques are currently applied to both the weights and activations; however, pruning is most often…

机器学习 · 计算机科学 2021-11-02 Xinyu Zhang , Ian Colbert , Ken Kreutz-Delgado , Srinjoy Das

Convolutional Neural Networks (CNNs) are pivotal in computer vision and Big Data analytics but demand significant computational resources when trained on large-scale datasets. Conventional training via back-propagation (BP) with losses like…

机器学习 · 计算机科学 2025-06-03 Aasish Kumar Sharma , Sanjeeb Prashad Pandey , Julian M. Kunkel

Spiking Neural Networks (SNNs) that operate in an event-driven manner and employ binary spike representation have recently emerged as promising candidates for energy-efficient computing. However, a cost bottleneck arises in obtaining…

神经与进化计算 · 计算机科学 2024-01-22 Yunpeng Yao , Man Wu , Zheng Chen , Renyuan Zhang

Modern Deep Neural Networks (DNNs) require significant memory to store weight, activations, and other intermediate tensors during training. Hence, many models do not fit one GPU device or can be trained using only a small per-GPU batch…

This paper addresses how a recursive neural network model can automatically leave out useless information and emphasize important evidence, in other words, to perform "weight tuning" for higher-level representation acquisition. We propose…

神经与进化计算 · 计算机科学 2014-12-16 Jiwei Li

Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. The program of an RNN is its weight matrix. How to learn useful representations of RNN weights that facilitate RNN analysis as well as downstream tasks?…

机器学习 · 计算机科学 2025-04-30 Vincent Herrmann , Francesco Faccio , Jürgen Schmidhuber

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) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are…

机器学习 · 计算机科学 2023-12-27 Gianni Franchi , Olivier Laurent , Maxence Leguéry , Andrei Bursuc , Andrea Pilzer , Angela Yao

Deep neural network models, though very powerful and highly successful, are computationally expensive in terms of space and time. Recently, there have been a number of attempts on binarizing the network weights and activations. This greatly…

神经与进化计算 · 计算机科学 2018-05-11 Lu Hou , Quanming Yao , James T. Kwok

In this work, we experimentally demonstrate two key building blocks for realizing Binary/Ternary Neural Networks (BNNs/TNNs): (i) 130 nm CMOS based sigmoidal neurons and (ii) HfOx based multi-level (MLC) OxRAM-synaptic blocks. An optimized…

新兴技术 · 计算机科学 2022-07-29 Sandeep Kaur Kingra , Vivek Parmar , Manoj Sharma , Manan Suri

Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e.g., image classification, natural language processing, etc. Despite the good performance, the huge number of parameters in DNNs brings…

机器学习 · 计算机科学 2020-12-21 Jinmian Ye , Guangxi Li , Di Chen , Haiqin Yang , Shandian Zhe , Zenglin Xu

Quantization of weights and activations in Deep Neural Networks (DNNs) is a powerful technique for network compression, and has enjoyed significant attention and success. However, much of the inference-time benefit of quantization is…

性能 · 计算机科学 2019-12-13 Andrew Anderson , David Gregg

Convolutional neural networks (CNNs) and transformers, which are composed of multiple processing layers and blocks to learn the representations of data with multiple abstract levels, are the most successful machine learning models in recent…

机器学习 · 计算机科学 2022-03-03 Biyi Fang , Jean Utke , Diego Klabjan
‹ 上一页 1 8 9 10 下一页 ›