English
Related papers

Related papers: Continuously Differentiable Exponential Linear Uni…

200 papers

We can compare the expressiveness of neural networks that use rectified linear units (ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise linear functions modeled by such networks. However,…

Machine Learning · Computer Science 2019-12-17 Thiago Serra , Srikumar Ramalingam

Feature normalization transforms such as Batch and Layer-Normalization have become indispensable ingredients of state-of-the-art deep neural networks. Recent studies on fine-tuning large pretrained models indicate that just tuning the…

Machine Learning · Computer Science 2023-07-06 Angeliki Giannou , Shashank Rajput , Dimitris Papailiopoulos

Activation functions play a key role in providing remarkable performance in deep neural networks, and the rectified linear unit (ReLU) is one of the most widely used activation functions. Various new activation functions and improvements on…

Machine Learning · Computer Science 2019-08-27 Yang Liu , Jianpeng Zhang , Chao Gao , Jinghua Qu , Lixin Ji

Growing evidence suggests that layer attention mechanisms, which enhance interaction among layers in deep neural networks, have significantly advanced network architectures. However, existing layer attention methods suffer from redundancy,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Hanze Li , Xiande Huang

Normalization techniques are important in different advanced neural networks and different tasks. This work investigates a novel dynamic learning-to-normalize (L2N) problem by proposing Exemplar Normalization (EN), which is able to learn…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Ruimao Zhang , Zhanglin Peng , Lingyun Wu , Zhen Li , Ping Luo

Many scientific and geometric problems exhibit general linear symmetries, yet most equivariant neural networks are built for compact groups or simple vector features, limiting their reuse on matrix-valued data such as covariances, inertias,…

Machine Learning · Computer Science 2026-02-02 Chankyo Kim , Sicheng Zhao , Minghan Zhu , Tzu-Yuan Lin , Maani Ghaffari

We study layered neural networks of rectified linear units (ReLU) in a modelling framework for stochastic training processes. The comparison with sigmoidal activation functions is in the center of interest. We compute typical learning…

Machine Learning · Computer Science 2020-11-13 Elisa Oostwal , Michiel Straat , Michael Biehl

The linear layer is one of the most pervasive modules in deep learning representations. However, it requires $O(N^2)$ parameters and $O(N^2)$ operations. These costs can be prohibitive in mobile applications or prevent scaling in many…

Machine Learning · Computer Science 2016-03-22 Marcin Moczulski , Misha Denil , Jeremy Appleyard , Nando de Freitas

An extreme learning machine (ELM) can be regarded as a two stage feed-forward neural network (FNN) learning system which randomly assigns the connections with and within hidden neurons in the first stage and tunes the connections with…

Machine Learning · Computer Science 2014-01-27 Shaobo Lin , Xia Liu , Jian Fang , Zongben Xu

For any skew symmetric matrix over complex numbers, we introduce an EALA and it is called Skew Symmetric Extended Affine Lie Algebra (SSEALA). This way we get a large class of EALAs and most often they are non-isomorphic. In this paper we…

Representation Theory · Mathematics 2026-02-16 S. Eswara Rao , Priyanshu Chakraborty

Activation function is a key component in deep learning that performs non-linear mappings between the inputs and outputs. Rectified Linear Unit (ReLU) has been the most popular activation function across the deep learning community.…

Machine Learning · Computer Science 2022-03-01 Hock Hung Chieng , Noorhaniza Wahid , Pauline Ong

Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change.…

Machine Learning · Computer Science 2022-03-29 Binghui Peng , Andrej Risteski

Following the idea of Subexponential Linear Logic and Stratified Bounded Linear Logic, we propose a new parameterized version of Linear Logic which subsumes other systems like ELL, LLL or SLL, by including variants of the exponential rules.…

Logic in Computer Science · Computer Science 2022-01-03 Esaïe Bauer , Olivier Laurent

In the past decade, deep learning became the prevalent methodology for predictive modeling thanks to the remarkable accuracy of deep neural networks in tasks such as computer vision and natural language processing. Meanwhile, the structure…

Optimization and Control · Mathematics 2025-09-16 Joey Huchette , Gonzalo Muñoz , Thiago Serra , Calvin Tsay

Extreme Learning Machines (ELM) provide a fast alternative to traditional gradient-based learning in neural networks, offering rapid training and robust generalization capabilities. Its theoretical basis shows its universal approximation…

Machine Learning · Computer Science 2024-06-27 Ergun Biçici

We revisit Deep Linear Discriminant Analysis (Deep LDA) from a likelihood-based perspective. While classical LDA is a simple Gaussian model with linear decision boundaries, attaching an LDA head to a neural encoder raises the question of…

Machine Learning · Statistics 2026-02-23 Maxat Tezekbayev , Arman Bolatov , Zhenisbek Assylbekov

Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. This prevents the feasibility of deployment on different input image resolutions for a specific model. To…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Duo Li , Anbang Yao , Qifeng Chen

A major challenge in the training of recurrent neural networks is the so-called vanishing or exploding gradient problem. The use of a norm-preserving transition operator can address this issue, but parametrization is challenging. In this…

Machine Learning · Statistics 2017-01-11 Stephanie L. Hyland , Gunnar Rätsch

When optimizing a nonlinear objective, one can employ a neural network as a surrogate for the nonlinear function. However, the resulting optimization model can be time-consuming to solve globally with exact methods. As a result, local…

Optimization and Control · Mathematics 2026-03-19 Jiatai Tong , Yilin Zhu , Thiago Serra , Samuel Burer

For many machine learning applications, a common input representation is a spectrogram. The underlying representation for a spectrogram is a short time Fourier transform (STFT) which gives complex values. The spectrogram uses the magnitude…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-28 Les Atlas , Nicholas Rasmussen , Felix Schwock , Mert Pilanci