中文
相关论文

相关论文: Layerwise Progressive Freezing Enables STE-Free Tr…

200 篇论文

Quantization and pruning are two effective Deep Neural Networks model compression methods. In this paper, we propose Automatic Prune Binarization (APB), a novel compression technique combining quantization with pruning. APB enhances the…

计算机视觉与模式识别 · 计算机科学 2023-09-18 Franco Maria Nardini , Cosimo Rulli , Salvatore Trani , Rossano Venturini

Dynamic Sparse Training (DST) methods train neural networks by maintaining sparsity while dynamically adapting the network topology. Despite the promise of reduced computation, DST methods converge significantly slower than dense training,…

机器学习 · 计算机科学 2026-05-28 Mohammed Adnan , Rohan Jain , Tom Jacobs , Ekansh Sharma , Rahul G. Krishnan , Rebekka Burkholz , Yani Ioannou

High-efficiency deep learning (DL) models are necessary not only to facilitate their use in devices with limited resources but also to improve resources required for training. Convolutional neural networks (ConvNets) typically exert severe…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Christos Kyrkou

The compression of deep neural networks (DNNs) to reduce inference cost becomes increasingly important to meet realistic deployment requirements of various applications. There have been a significant amount of work regarding network…

机器学习 · 计算机科学 2020-11-12 Tianyi Chen , Bo Ji , Yixin Shi , Tianyu Ding , Biyi Fang , Sheng Yi , Xiao Tu

Modern neural network training relies on piece-wise (sub-)differentiable functions in order to use backpropagation to update model parameters. In this work, we introduce a novel method to allow simple non-differentiable functions at…

机器学习 · 计算机科学 2019-10-29 Jason Ramapuram , Russ Webb

Quantized or low-bit neural networks are attractive due to their inference efficiency. However, training deep neural networks with quantized activations involves minimizing a discontinuous and piecewise constant loss function. Such a loss…

机器学习 · 计算机科学 2021-06-15 Ziang Long , Penghang Yin , Jack Xin

While hardware implementations of inference routines for Binarized Neural Networks (BNNs) are plentiful, current realizations of efficient BNN hardware training accelerators, suitable for Internet of Things (IoT) edge devices, leave much to…

计算机视觉与模式识别 · 计算机科学 2021-02-18 Corey Lammie , Wei Xiang , Mostafa Rahimi Azghadi

The memristive crossbar aims to implement analog weighted neural network, however, the realistic implementation of such crossbar arrays is not possible due to limited switching states of memristive devices. In this work, we propose the…

新兴技术 · 计算机科学 2018-08-03 Olga Krestinskaya , Alex Pappachen James

Compared to Multilayer Neural Networks with real weights, Binary Multilayer Neural Networks (BMNNs) can be implemented more efficiently on dedicated hardware. BMNNs have been demonstrated to be effective on binary classification tasks with…

神经与进化计算 · 计算机科学 2015-03-24 Zhiyong Cheng , Daniel Soudry , Zexi Mao , Zhenzhong Lan

In this paper, we consider deep neural networks for solving inverse problems that are robust to forward model mis-specifications. Specifically, we treat sensing problems with model mismatch where one wishes to recover a sparse…

机器学习 · 计算机科学 2021-10-22 Wei Pu , Chao Zhou , Yonina C. Eldar , Miguel R. D. Rodrigues

The discontinuous operations inherent in quantization and sparsification introduce a long-standing obstacle to backpropagation, particularly in ultra-low precision and sparse regimes. While the community has long viewed quantization as…

机器学习 · 计算机科学 2026-03-11 Chengxi Ye , Grace Chu , Yanfeng Liu , Yichi Zhang , Lukasz Lew , Li Zhang , Mark Sandler , Andrew Howard

Compared with artificial neural networks (ANNs), spiking neural networks (SNNs) are promising to explore the brain-like behaviors since the spikes could encode more spatio-temporal information. Although pre-training from ANN or direct…

神经与进化计算 · 计算机科学 2018-09-18 Yujie Wu , Lei Deng , Guoqi Li , Jun Zhu , Luping Shi

This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may…

计算机视觉与模式识别 · 计算机科学 2021-06-07 Bohan Zhuang , Jing Liu , Mingkui Tan , Lingqiao Liu , Ian Reid , Chunhua Shen

Optimal decision making requires that classifiers produce uncertainty estimates consistent with their empirical accuracy. However, deep neural networks are often under- or over-confident in their predictions. Consequently, methods have been…

Batch normalization (BN) is a key facilitator and considered essential for state-of-the-art binary neural networks (BNN). However, the BN layer is costly to calculate and is typically implemented with non-binary parameters, leaving a hurdle…

机器学习 · 计算机科学 2021-04-19 Tianlong Chen , Zhenyu Zhang , Xu Ouyang , Zechun Liu , Zhiqiang Shen , Zhangyang Wang

Recent results show that deep neural networks achieve excellent performance even when, during training, weights are quantized and projected to a binary representation. Here, we show that this is just the tip of the iceberg: these same…

神经与进化计算 · 计算机科学 2016-06-08 Paul Merolla , Rathinakumar Appuswamy , John Arthur , Steve K. Esser , Dharmendra Modha

Despite the notable success of deep neural networks (DNNs) in solving complex tasks, the training process still remains considerable challenges. A primary obstacle is the substantial time required for training, particularly as high…

机器学习 · 计算机科学 2025-09-09 Viet Hoang Pham , Hyo-Sung Ahn

Analog Compute-In-Memory (CIM) architectures promise significant energy efficiency gains for neural network inference, but suffer from complex hardware-induced noise that poses major challenges for deployment. While noise-aware training…

机器学习 · 计算机科学 2025-08-19 Yuannuo Feng , Wenyong Zhou , Yuexi Lyu , Yixiang Zhang , Zhengwu Liu , Ngai Wong , Wang Kang

Significant success has been reported recently using deep neural networks for classification. Such large networks can be computationally intensive, even after training is over. Implementing these trained networks in hardware chips with a…

机器学习 · 统计学 2013-10-25 Daniel Soudry , Ron Meir

We present a method to train self-binarizing neural networks, that is, networks that evolve their weights and activations during training to become binary. To obtain similar binary networks, existing methods rely on the sign activation…

计算机视觉与模式识别 · 计算机科学 2019-02-05 Fayez Lahoud , Radhakrishna Achanta , Pablo Márquez-Neila , Sabine Süsstrunk