English
Related papers

Related papers: Rethink ReLU to Training Better CNNs

200 papers

In this paper, we present a novel and general network structure towards accelerating the inference process of convolutional neural networks, which is more complicated in network structure yet with less inference complexity. The core idea is…

Computer Vision and Pattern Recognition · Computer Science 2017-05-16 Xuanyi Dong , Junshi Huang , Yi Yang , Shuicheng Yan

Neural networks in general, from MLPs and CNNs to attention-based Transformers, are constructed from layers of linear combinations followed by nonlinear operations such as ReLU, Sigmoid, or Softmax. Despite their strength, these…

Machine Learning · Computer Science 2025-10-09 Weiguo Lu , Gangnan Yuan , Hong-kun Zhang , Shangyang Li

Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having around 152 layers.…

Machine Learning · Computer Science 2024-02-20 Chinmay Rane , Kanishka Tyagi , Michael Manry

Convolutional neural networks have shown impressive abilities in many applications, especially those related to the classification tasks. However, for the regression problem, the abilities of convolutional structures have not been fully…

Machine Learning · Computer Science 2023-01-23 Zhiying Fang , Guang Cheng

Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, we propose a Parametric Rectified Linear Unit…

Computer Vision and Pattern Recognition · Computer Science 2015-02-09 Kaiming He , Xiangyu Zhang , Shaoqing Ren , Jian Sun

The training process of neural networks usually optimize weights and bias parameters of linear transformations, while nonlinear activation functions are pre-specified and fixed. This work develops a systematic approach to constructing…

Machine Learning · Computer Science 2024-10-29 Zhengqi Liu , Shuhao Cao , Yuwen Li , Ludmil Zikatanov

It has been widely assumed that a neural network cannot be recovered from its outputs, as the network depends on its parameters in a highly nonlinear way. Here, we prove that in fact it is often possible to identify the architecture,…

Machine Learning · Computer Science 2020-02-25 David Rolnick , Konrad P. Kording

Many classes of images exhibit rotational symmetry. Convolutional neural networks are sometimes trained using data augmentation to exploit this, but they are still required to learn the rotation equivariance properties from the data.…

Machine Learning · Computer Science 2016-05-27 Sander Dieleman , Jeffrey De Fauw , Koray Kavukcuoglu

Rectified linear activation units are important components for state-of-the-art deep convolutional networks. In this paper, we propose a novel S-shaped rectified linear activation unit (SReLU) to learn both convex and non-convex functions,…

Computer Vision and Pattern Recognition · Computer Science 2015-12-23 Xiaojie Jin , Chunyan Xu , Jiashi Feng , Yunchao Wei , Junjun Xiong , Shuicheng Yan

This work attempts to address two fundamental questions about the structure of the convolutional neural networks (CNN): 1) why a non-linear activation function is essential at the filter output of every convolutional layer? 2) what is the…

Computer Vision and Pattern Recognition · Computer Science 2016-11-04 C. -C. Jay Kuo

In this paper we investigate the family of functions representable by deep neural networks (DNN) with rectified linear units (ReLU). We give an algorithm to train a ReLU DNN with one hidden layer to *global optimality* with runtime…

Machine Learning · Computer Science 2018-03-01 Raman Arora , Amitabh Basu , Poorya Mianjy , Anirbit Mukherjee

Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy. Due to this, in modern CNN architectures, it becomes more important to…

Machine Learning · Computer Science 2019-05-14 Jongheon Jeong , Jinwoo Shin

This paper proposes a learnable nonlinear activation mechanism specifically for convolutional neural network (CNN) termed as LENI, which learns to enhance the negative information in CNNs. In sharp contrast to ReLU which cuts off the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Zhicheng Cai , Chenglei Peng , Qiu Shen

Neural networks have been widely used, and most networks achieve excellent performance by stacking certain types of basic units. Compared to increasing the depth and width of the network, designing more effective basic units has become an…

Machine Learning · Computer Science 2020-06-05 Junyi An , Fengshan Liu , Jian Zhao , Furao Shen

Element-wise activation functions play a critical role in deep neural networks via affecting the expressivity power and the learning dynamics. Learning-based activation functions have recently gained increasing attention and success. We…

Machine Learning · Computer Science 2020-10-05 Dengsheng Chen , Jun Li , Kai Xu

The Rectified Linear Unit is currently a state-of-the-art activation function in deep convolutional neural networks. To combat ReLU's dying neuron problem, we propose the Parametric Variational Linear Unit (PVLU), which adds a sinusoidal…

Computer Vision and Pattern Recognition · Computer Science 2021-12-20 Aarush Gupta , Shikhar Ahuja

Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the…

Machine Learning · Statistics 2019-05-01 Gang Wang , Georgios B. Giannakis , Jie Chen

Activation functions play a vital role in the training of Convolutional Neural Networks. For this reason, to develop efficient and performing functions is a crucial problem in the deep learning community. Key to these approaches is to…

Computer Vision and Pattern Recognition · Computer Science 2020-09-23 Gianluca Maguolo , Loris Nanni , Stefano Ghidoni

It has been shown that neural network classifiers are not robust. This raises concerns about their usage in safety-critical systems. We propose in this paper a regularization scheme for ReLU networks which provably improves the robustness…

Machine Learning · Computer Science 2019-03-11 Francesco Croce , Maksym Andriushchenko , Matthias Hein

In this work, we propose to train a deep neural network by distributed optimization over a graph. Two nonlinear functions are considered: the rectified linear unit (ReLU) and a linear unit with both lower and upper cutoffs (DCutLU). The…

Machine Learning · Computer Science 2017-06-20 Guoqiang Zhang , W. Bastiaan Kleijn
‹ Prev 1 3 4 5 6 7 10 Next ›