English
Related papers

Related papers: SAU: Smooth activation function using convolution …

200 papers

In this work, we consider the approximation of a large class of bounded functions, with minimal regularity assumptions, by ReLU neural networks. We show that the approximation error can be bounded from above by a quantity proportional to…

Machine Learning · Statistics 2026-02-27 Owen Davis , Gianluca Geraci , Mohammad Motamed

Sparse autoencoders (SAEs) are a promising unsupervised approach for identifying causally relevant and interpretable linear features in a language model's (LM) activations. To be useful for downstream tasks, SAEs need to decompose LM…

Machine Learning · Computer Science 2024-08-02 Senthooran Rajamanoharan , Tom Lieberum , Nicolas Sonnerat , Arthur Conmy , Vikrant Varma , János Kramár , Neel Nanda

Deep neural networks have recently achieved state-of-the-art results in many machine learning problems, e.g., speech recognition or object recognition. Hitherto, work on rectified linear units (ReLU) provides empirical and theoretical…

Machine Learning · Computer Science 2015-05-12 Jakub Mikolaj Tomczak

LayerNorm is a critical component in modern large language models (LLMs) for stabilizing training and ensuring smooth optimization. However, it introduces significant challenges in mechanistic interpretability, outlier feature suppression,…

Machine Learning · Computer Science 2024-11-19 Nandan Kumar Jha , Brandon Reagen

Outsourcing deep neural networks (DNNs) inference tasks to an untrusted cloud raises data privacy and integrity concerns. While there are many techniques to ensure privacy and integrity for polynomial-based computations, DNNs involve…

Machine Learning · Computer Science 2024-02-07 Ramy E. Ali , Jinhyun So , A. Salman Avestimehr

Despite their prevalence in neural networks we still lack a thorough theoretical characterization of ReLU layers. This paper aims to further our understanding of ReLU layers by studying how the activation function ReLU interacts with the…

Machine Learning · Computer Science 2019-08-13 Sören Dittmer , Emily J. King , Peter Maass

In the last decade, an active area of research has been devoted to design novel activation functions that are able to help deep neural networks to converge, obtaining better performance. The training procedure of these architectures usually…

Machine Learning · Computer Science 2019-04-26 Franco Manessi , Alessandro Rozza

In this paper, we revise two commonly used saturated functions, the logistic sigmoid and the hyperbolic tangent (tanh). We point out that, besides the well-known non-zero centered property, slope of the activation function near the origin…

Machine Learning · Computer Science 2016-05-03 Bing Xu , Ruitong Huang , Mu Li

Neural networks are universal function approximators which are known to generalize well despite being dramatically overparameterized. We study this phenomenon from the point of view of the spectral bias of neural networks. Our contributions…

Machine Learning · Computer Science 2022-09-07 Qingguo Hong , Jonathan W. Siegel , Qinyang Tan , Jinchao Xu

Rectified linear units (ReLU) are commonly used in deep neural networks. So far ReLU and its generalizations (non-parametric or parametric) are static, performing identically for all input samples. In this paper, we propose dynamic ReLU…

Computer Vision and Pattern Recognition · Computer Science 2020-08-06 Yinpeng Chen , Xiyang Dai , Mengchen Liu , Dongdong Chen , Lu Yuan , Zicheng Liu

The activation functions are fundamental to neural networks as they introduce non-linearity into data relationships, thereby enabling deep networks to approximate complex data relations. Existing efforts to enhance neural network…

Machine Learning · Computer Science 2024-09-26 Jiayu Li , Zilong Zhao , Kevin Yee , Uzair Javaid , Biplab Sikdar

We consider the approximation rates of shallow neural networks with respect to the variation norm. Upper bounds on these rates have been established for sigmoidal and ReLU activation functions, but it has remained an important open problem…

Machine Learning · Statistics 2021-09-10 Jonathan W. Siegel , Jinchao Xu

We propose the Gaussian Error Linear Unit (GELU), a high-performing neural network activation function. The GELU activation function is $x\Phi(x)$, where $\Phi(x)$ the standard Gaussian cumulative distribution function. The GELU…

Machine Learning · Computer Science 2023-06-07 Dan Hendrycks , Kevin Gimpel

With the continuous growth of neural network scales, low-precision quantization is widely used in edge accelerators. Classic multi-threshold activation hardware requires 2^n thresholds for n-bit outputs, causing a rapid increase in hardware…

Hardware Architecture · Computer Science 2026-02-27 Yuhao Liu , Salim Ullah , Akash Kumar

We study approximation and statistical learning properties of deep ReLU networks under structural assumptions that mitigate the curse of dimensionality. We prove minimax-optimal uniform approximation rates for $s$-H\"older smooth functions…

Statistics Theory · Mathematics 2026-02-06 Thomas Nagler , Sophie Langer

The rectified linear unit (ReLU) is a highly successful activation function in neural networks as it allows networks to easily obtain sparse representations, which reduces overfitting in overparameterized networks. However, in network…

Machine Learning · Computer Science 2022-12-14 Shiyu Liu , Rohan Ghosh , Dylan Tan , Mehul Motani

The most widely used activation functions in current deep feed-forward neural networks are rectified linear units (ReLU), and many alternatives have been successfully applied, as well. However, none of the alternatives have managed to…

Machine Learning · Computer Science 2018-06-27 Leon René Sütfeld , Flemming Brieger , Holger Finger , Sonja Füllhase , Gordon Pipa

The widespread application of artificial neural networks has prompted researchers to experiment with FPGA and customized ASIC designs to speed up their computation. These implementation efforts have generally focused on weight…

Neural and Evolutionary Computing · Computer Science 2018-10-23 Tao Yang , Yadong Wei , Zhijun Tu , Haolun Zeng , Michel A. Kinsy , Nanning Zheng , Pengju Ren

In recent years, the computational demands of deep learning applications have necessitated the introduction of energy-efficient hardware accelerators. Optical neural networks are a promising option; however, thus far they have been largely…

Modern DNN workloads increasingly rely on activation functions consisting of computationally complex operations. This poses a challenge to current accelerators optimized for convolutions and matrix-matrix multiplications. This work presents…

Hardware Architecture · Computer Science 2023-05-09 Enrico Reggiani , Renzo Andri , Lukas Cavigelli