English
Related papers

Related papers: Hardware Realization of Nonlinear Activation Funct…

200 papers

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

In this article we present new results on neural networks with linear threshold activation functions. We precisely characterize the class of functions that are representable by such neural networks and show that 2 hidden layers are…

Machine Learning · Computer Science 2023-10-20 Sammy Khalife , Hongyu Cheng , Amitabh Basu

Random feature model with a nonlinear activation function has been shown to perform asymptotically equivalent to a Gaussian model in terms of training and generalization errors. Analysis of the equivalent model reveals an important yet not…

Machine Learning · Computer Science 2023-10-02 Samet Demir , Zafer Doğan

The development of viable all-optical data processing systems has immense importance for both the computing and telecommunication industries, but device realization remains elusive. In this Letter, we propose an innovative mechanism…

Optics · Physics 2012-06-21 David L. Andrews , David S. Bradshaw

We are interested in assessing the use of neural networks as surrogate models to approximate and minimize objective functions in optimization problems. While neural networks are widely used for machine learning tasks such as classification…

Machine Learning · Computer Science 2023-11-22 Tommaso Giovannelli , Oumaima Sohab , Luis Nunes Vicente

Proximal algorithms have gained popularity in recent years in large-scale and distributed optimization problems. One such problem is the phase retrieval problem, for which proximal operators have been proposed recently. The phase retrieval…

Optimization and Control · Mathematics 2018-08-16 Biel Roig-Solvas , Lee Makowski , Dana H. Brooks

In this paper, a novel neural network activation function, called Symmetrical Gaussian Error Linear Unit (SGELU), is proposed to obtain high performance. It is achieved by effectively integrating the property of the stochastic regularizer…

Machine Learning · Computer Science 2019-11-12 Chao Yu , Zhiguo Su

In order to improve the least mean squares (LMS) adaptation algorithm to accommodate the nonlinear transfer function, and to adjust the coefficients of adaptive filter during the actual implement of bias voltage and signal amplitude,…

Signal Processing · Electrical Eng. & Systems 2022-07-26 Zhengyang Zhang

We introduce a proximal version of dual coordinate ascent method. We demonstrate how the derived algorithmic framework can be used for numerous regularized loss minimization problems, including $\ell_1$ regularization and structured output…

Machine Learning · Statistics 2012-11-13 Shai Shalev-Shwartz , Tong Zhang

We study the problem of formal verification of Binarized Neural Networks (BNN), which have recently been proposed as a energy-efficient alternative to traditional learning networks. The verification of BNNs, using the reduction to hardware…

Software Engineering · Computer Science 2018-01-22 Chih-Hong Cheng , Georg Nührenberg , Chung-Hao Huang , Harald Ruess

The miniaturization of transistors down to 5nm and beyond, plus the increasing complexity of integrated circuits, significantly aggravate short channel effects, and demand analysis and optimization of more design corners and modes.…

Machine Learning · Computer Science 2020-02-14 Mohammad Saeed Abrishami , Massoud Pedram , Shahin Nazarian

The article is devoted to the study of neural networks with one hidden layer and a modified activation function for solving physical problems. A rectified sigmoid activation function has been proposed to solve physical problems described by…

Numerical Analysis · Mathematics 2024-12-31 Vasiliy A. Es'kin , Alexey O. Malkhanov , Mikhail E. Smorkalov

Orthogonal signal-division multiplexing (OSDM) is an attractive alternative to conventional orthogonal frequency-division multiplexing (OFDM) due to its enhanced ability in peak-to-average power ratio (PAPR) reduction. Combining OSDM with…

Signal Processing · Electrical Eng. & Systems 2019-06-27 Jing Han , Shengqian Ma , Yujie Wang , Geert Leus

Neural networks with low-precision weights and activations offer compelling efficiency advantages over their full-precision equivalents. The two most frequently discussed benefits of quantization are reduced memory consumption, and a faster…

Machine Learning · Computer Science 2018-02-01 Angus Galloway , Graham W. Taylor , Medhat Moussa

We present a 'calculator' for constructing a homogeneous approximation of nonlinear control systems, which is based on the algebraic approach developed by the authors in their previous papers. This approach mainly uses linear algebraic and…

Optimization and Control · Mathematics 2021-12-01 Grigory Sklyar , Pavel Barkhayev , Svetlana Ignatovich , Viktor Rusakov

Image deblurring remains a central research area within image processing, critical for its role in enhancing image quality and facilitating clearer visual representations across diverse applications. This paper tackles the optimization…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Qingsong Wang , Shengze Xu , Xiaojiao Tong , Tieyong Zeng

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

Non-linear operations such as GELU, Layer normalization, and Softmax are essential yet costly building blocks of Transformer models. Several prior works simplified these operations with look-up tables or integer computations, but such…

Machine Learning · Computer Science 2021-12-07 Joonsang Yu , Junki Park , Seongmin Park , Minsoo Kim , Sihwa Lee , Dong Hyun Lee , Jungwook Choi

We prove some new results concerning the approximation rate of neural networks with general activation functions. Our first result concerns the rate of approximation of a two layer neural network with a polynomially-decaying non-sigmoidal…

Classical Analysis and ODEs · Mathematics 2021-01-05 Jonathan W. Siegel , Jinchao Xu

Many promising applications of quantum computing with a provable speedup center around the HHL algorithm. Due to restrictions on the hardware and its significant demand on qubits and gates in known implementations, its execution is…