English
Related papers

Related papers: Improving Deep Learning by Inverse Square Root Lin…

200 papers

Modeling sophisticated activation functions within deep learning architectures has evolved into a distinct research direction. Functions such as GELU, SELU, and SiLU offer smooth gradients and improved convergence properties, making them…

Recurrent neural networks (RNNs) have represented for years the state of the art in neural machine translation. Recently, new architectures have been proposed, which can leverage parallel computation on GPUs better than classical RNNs.…

Computation and Language · Computer Science 2018-05-14 Mattia Antonino Di Gangi , Marcello Federico

Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural…

Machine Learning · Computer Science 2019-05-21 MohamadAli Torkamani , Phillip Wallis , Shiv Shankar , Amirmohammad Rooshenas

Supervised Deep-Learning (DL)-based reconstruction algorithms have shown state-of-the-art results for highly-undersampled dynamic Magnetic Resonance Imaging (MRI) reconstruction. However, the requirement of excessive high-quality…

Image and Video Processing · Electrical Eng. & Systems 2025-11-11 Jie Feng , Ruimin Feng , Qing Wu , Zhiyong Zhang , Yuyao Zhang , Hongjiang Wei

This paper introduces and evaluates a novel training method for neural networks: Dual Variable Learning Rates (DVLR). Building on insights from behavioral psychology, the dual learning rates are used to emphasize correct and incorrect…

Machine Learning · Computer Science 2021-02-11 Elizabeth Liner , Risto Miikkulainen

Linear recurrent neural networks, such as State Space Models (SSMs) and Linear Recurrent Units (LRUs), have recently shown state-of-the-art performance on long sequence modelling benchmarks. Despite their success, their empirical…

Machine Learning · Computer Science 2024-10-08 Kai Biegun , Rares Dolga , Jake Cunningham , David Barber

As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality.…

Computer Vision and Pattern Recognition · Computer Science 2016-08-02 Chao Dong , Chen Change Loy , Xiaoou Tang

Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference. These architectures hold promise for streaming applications at the edge, but deployment in…

Machine Learning · Computer Science 2025-08-14 Alessandro Pierro , Steven Abreu , Jonathan Timcheck , Philipp Stratmann , Andreas Wild , Sumit Bam Shrestha

Machine learning applications are computationally demanding and power intensive. Hardware acceleration of these software tools is a natural step being explored using various technologies. A recurrent processing unit (RPU) is fast and…

Emerging Technologies · Computer Science 2019-12-17 Heidi Komkov , Alessandro Restelli , Brian Hunt , Liam Shaughnessy , Itamar Shani , Daniel P. Lathrop

Convolutional neural networks (CNNs) attained a good performance in hyperspectral sensing image (HSI) classification, but CNNs consider spectra as orderless vectors. Therefore, considering the spectra as sequences, recurrent neural networks…

Machine Learning · Computer Science 2018-10-31 Haowen Luo

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

This paper introduces a new Dynamic Gated Recurrent Neural Network (DG-RNN) for compute-efficient speech enhancement models running on resource-constrained hardware platforms. It leverages the slow evolution characteristic of RNN hidden…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Longbiao Cheng , Ashutosh Pandey , Buye Xu , Tobi Delbruck , Shih-Chii Liu

This paper presents a basic property of region dividing of ReLU (rectified linear unit) deep learning when new layers are successively added, by which two new perspectives of interpreting deep learning are given. The first is related to…

Machine Learning · Computer Science 2019-12-09 Changcun Huang

Accelerating the deep learning inference is very important for real-time applications. In this paper, we propose a novel method to fuse the layers of convolutional neural networks (CNNs) on Graphics Processing Units (GPUs), which applies…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-07-30 Xueying Wang , Guangli Li , Xiao Dong , Jiansong Li , Lei Liu , Xiaobing Feng

Object recognition is an important task for improving the ability of visual systems to perform complex scene understanding. Recently, the Exponential Linear Unit (ELU) has been proposed as a key component for managing bias shift in…

Machine Learning · Computer Science 2018-01-11 Ludovic Trottier , Philippe Giguère , Brahim Chaib-draa

We consider the computational complexity of training depth-2 neural networks composed of rectified linear units (ReLUs). We show that, even for the case of a single ReLU, finding a set of weights that minimizes the squared error (even…

Computational Complexity · Computer Science 2018-10-17 Pasin Manurangsi , Daniel Reichman

We describe an algorithm that learns two-layer residual units using rectified linear unit (ReLU) activation: suppose the input $\mathbf{x}$ is from a distribution with support space $\mathbb{R}^d$ and the ground-truth generative model is a…

Machine Learning · Computer Science 2022-12-13 Zhunxuan Wang , Linyun He , Chunchuan Lyu , Shay B. Cohen

Despite their impressive performance, Deep Neural Networks (DNNs) typically underperform Gradient Boosting Trees (GBTs) on many tabular-dataset learning tasks. We propose that applying a different regularization coefficient to each weight…

Machine Learning · Statistics 2018-10-25 Ira Shavitt , Eran Segal

Neural networks with at least two hidden layers are called deep networks. Recent developments in AI and computer programming in general has led to development of tools such as Tensorflow, Keras, NumPy etc. making it easier to model and draw…

Signal Processing · Electrical Eng. & Systems 2021-03-30 Ruthvik Vaila , Denver Lloyd , Kevin Tetz

A recent line of work shows that a deep neural network with ReLU nonlinearities arises from a finite sequence of cascaded sparse coding models, the outputs of which, except for the last element in the cascade, are sparse and unobservable.…

Signal Processing · Electrical Eng. & Systems 2020-04-27 Demba Ba