中文
相关论文

相关论文: 0/1 Deep Neural Networks via Block Coordinate Desc…

200 篇论文

Optimization techniques are of great importance to effectively and efficiently train a deep neural network (DNN). It has been shown that using the first and second order statistics (e.g., mean and variance) to perform Z-score…

计算机视觉与模式识别 · 计算机科学 2020-04-09 Hongwei Yong , Jianqiang Huang , Xiansheng Hua , Lei Zhang

Despite the recent success of stochastic gradient descent in deep learning, it is often difficult to train a deep neural network with an inappropriate choice of its initial parameters. Even if training is successful, it has been known that…

机器学习 · 计算机科学 2023-02-10 Cheolhyoung Lee , Kyunghyun Cho

Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks (SNNs) than artificial neural networks (ANNs). This is…

神经与进化计算 · 计算机科学 2023-11-21 Ana Stanojevic , Stanisław Woźniak , Guillaume Bellec , Giovanni Cherubini , Angeliki Pantazi , Wulfram Gerstner

Background: It is still an open research area to theoretically understand why Deep Neural Networks (DNNs)---equipped with many more parameters than training data and trained by (stochastic) gradient-based methods---often achieve remarkably…

机器学习 · 计算机科学 2018-11-30 Zhiqin John Xu

Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during…

机器学习 · 计算机科学 2021-06-16 Rui Zhang , Ziheng Jiao , Hongyuan Zhang , Xuelong Li

Activation functions play a decisive role in determining the capacity of Deep Neural Networks as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions…

计算机视觉与模式识别 · 计算机科学 2023-05-31 Jamshaid Ul Rahman , Faiza Makhdoom , Dianchen Lu

Training Artificial Neural Networks poses a challenging and critical problem in machine learning. Despite the effectiveness of gradient-based learning methods, such as Stochastic Gradient Descent (SGD), in training neural networks, they do…

Second-order optimizers hold intriguing potential for deep learning, but suffer from increased cost and sensitivity to the non-convexity of the loss surface as compared to gradient-based approaches. We introduce a coordinate descent method…

机器学习 · 计算机科学 2020-06-19 Ravi G. Patel , Nathaniel A. Trask , Mamikon A. Gulian , Eric C. Cyr

We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time. At training-time the binary weights and activations are used for computing the parameters gradients. During…

机器学习 · 计算机科学 2016-03-18 Matthieu Courbariaux , Itay Hubara , Daniel Soudry , Ran El-Yaniv , Yoshua Bengio

Deep neural networks (DNNs) have shown very promising results for various image restoration (IR) tasks. However, the design of network architectures remains a major challenging for achieving further improvements. While most existing…

计算机视觉与模式识别 · 计算机科学 2020-10-28 Weisheng Dong , Peiyao Wang , Wotao Yin , Guangming Shi , Fangfang Wu , Xiaotong Lu

Deep neural networks (DNNs) form the backbone of almost every state-of-the-art technique in the fields such as computer vision, speech processing, and text analysis. The recent advances in computational technology have made the use of DNNs…

机器学习 · 计算机科学 2018-03-20 Saiprasad Koturwar , Shabbir Merchant

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…

计算机视觉与模式识别 · 计算机科学 2019-09-10 Fuqiang Liu , C. Liu

Linear programs (LPs) can be solved by polynomially many moves along the circuit direction improving the objective the most, so-called deepest-descent steps (dd-steps). Computing these steps is NP-hard (De Loera et al., arXiv, 2019), a…

最优化与控制 · 数学 2021-01-26 Steffen Borgwardt , Cornelius Brand , Andreas Emil Feldmann , Martin Koutecký

Deep Neural Networks (DNNs) have two key deficiencies, their dependence on high precision computing and their inability to perform sequential learning, that is, when a DNN is trained on a first task and the same DNN is trained on the next…

神经与进化计算 · 计算机科学 2020-07-14 Ruthvik Vaila , John Chiasson , Vishal Saxena

Motivated by the gap between theoretical optimal approximation rates of deep neural networks (DNNs) and the accuracy realized in practice, we seek to improve the training of DNNs. The adoption of an adaptive basis viewpoint of DNNs leads to…

机器学习 · 计算机科学 2019-12-11 Eric C. Cyr , Mamikon A. Gulian , Ravi G. Patel , Mauro Perego , Nathaniel A. Trask

We use Deep Convolutional Neural Networks (DCNNs) for image segmentation problems. DCNNs can well extract the features from natural images. However, the classification functions in the existing network architecture of CNNs are simple and…

计算机视觉与模式识别 · 计算机科学 2020-02-11 Jun Liu , Xiangyue Wang , Xue-cheng Tai

In this paper, we propose a generalization of the Batch Normalization (BN) algorithm, diminishing batch normalization (DBN), where we update the BN parameters in a diminishing moving average way. BN is very effective in accelerating the…

机器学习 · 计算机科学 2019-02-20 Yintai Ma , Diego Klabjan

The backpropagation algorithm remains the dominant and most successful method for training deep neural networks (DNNs). At the same time, training DNNs at scale comes at a significant computational cost and therefore a high carbon…

机器学习 · 计算机科学 2025-11-12 Sander Dalm , Joshua Offergeld , Nasir Ahmad , Marcel van Gerven

Deep neural networks (DNNs) have successfully been applied in many fields in the past decades. However, the increasing number of multiply-and-accumulate (MAC) operations in DNNs prevents their application in resource-constrained and…

机器学习 · 计算机科学 2022-11-29 Wenhao Sun , Grace Li Zhang , Xunzhao Yin , Cheng Zhuo , Huaxi Gu , Bing Li , Ulf Schlichtmann

Computation using brain-inspired spiking neural networks (SNNs) with neuromorphic hardware may offer orders of magnitude higher energy efficiency compared to the current analog neural networks (ANNs). Unfortunately, training SNNs with the…

神经与进化计算 · 计算机科学 2020-06-09 Eimantas Ledinauskas , Julius Ruseckas , Alfonsas Juršėnas , Giedrius Buračas