English
Related papers

Related papers: Large Deviations of Gaussian Neural Networks with …

200 papers

In past few years, linear rectified unit activation functions have shown its significance in the neural networks, surpassing the performance of sigmoid activations. RELU (Nair & Hinton, 2010), ELU (Clevert et al., 2015), PRELU (He et al.,…

Machine Learning · Computer Science 2020-06-05 Vijay Pandey

We demonstrate that deep neural networks with the ReLU activation function can efficiently approximate the solutions of various types of parametric linear transport equations. For non-smooth initial conditions, the solutions of these PDEs…

Numerical Analysis · Mathematics 2020-01-31 Fabian Laakmann , Philipp Petersen

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

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

It is difficult to describe in mathematical terms what a neural network trained on data represents. On the other hand, there is a growing mathematical understanding of what neural networks are in principle capable of representing.…

Machine Learning · Computer Science 2025-06-25 Daan Huybrechs

In this paper, we have extended the well-established universal approximator theory to neural networks that use the unbounded ReLU activation function and a nonlinear softmax output layer. We have proved that a sufficiently large neural…

Machine Learning · Computer Science 2020-02-12 Behnam Asadi , Hui Jiang

The strong lottery ticket hypothesis has highlighted the potential for training deep neural networks by pruning, which has inspired interesting practical and theoretical insights into how neural networks can represent functions. For…

Machine Learning · Computer Science 2023-01-10 Rebekka Burkholz

Appropriate weight initialization settings, along with the ReLU activation function, have become cornerstones of modern deep learning, enabling the training and deployment of highly effective and efficient neural network models across…

Machine Learning · Computer Science 2024-04-02 Hyunwoo Lee , Yunho Kim , Seung Yeop Yang , Hayoung Choi

An example of an activation function $\sigma$ is given such that networks with activations $\{\sigma, \lfloor\cdot\rfloor\}$, integer weights and a fixed architecture depending on $d$ approximate continuous functions on $[0,1]^d$. The range…

Machine Learning · Statistics 2021-06-01 Aleksandr Beknazaryan

An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been…

Machine Learning · Computer Science 2019-12-30 Fayyaz ul Amir Afsar Minhas , Amina Asif

A general procedure for introducing parametric, learned, nonlinearity into activation functions is found to enhance the accuracy of representative neural networks without requiring significant additional computational resources. Examples…

Machine Learning · Computer Science 2025-05-14 David Yevick

Quantile regression is the task of estimating a specified percentile response, such as the median, from a collection of known covariates. We study quantile regression with rectified linear unit (ReLU) neural networks as the chosen model…

Statistics Theory · Mathematics 2020-12-21 Oscar Hernan Madrid Padilla , Wesley Tansey , Yanzhen Chen

In this paper, we investigate the expressivity and approximation properties of deep neural networks employing the ReLU$^k$ activation function for $k \geq 2$. Although deep ReLU networks can approximate polynomials effectively, deep…

Machine Learning · Computer Science 2024-01-12 Juncai He , Tong Mao , Jinchao Xu

Neural networks are powerful functions with widespread use, but the theoretical behaviour of these functions is not fully understood. Creating deep neural networks by stacking many layers has achieved exceptional performance in many…

Machine Learning · Computer Science 2024-08-16 Cameron Jakub , Mihai Nica

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 2019-09-10 MohamadAli Torkamani , Shiv Shankar , Amirmohammad Rooshenas , Phillip Wallis

We study the asymptotic law of a network of interacting neurons when the number of neurons becomes infinite. Given a completely connected network of firing rate neurons in which the synaptic weights are Gaussian correlated random variables,…

Probability · Mathematics 2013-06-03 Olivier Faugeras , James MacLaurin

In this work, we study large deviation properties of the covariance process in fully connected Gaussian deep neural networks. More precisely, we establish a large deviation principle (LDP) for the covariance process in a functional…

Probability · Mathematics 2025-05-14 Luisa Andreis , Federico Bassetti , Christian Hirsch

Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the…

Machine Learning · Computer Science 2019-10-01 Farnoush Farhadi , Vahid Partovi Nia , Andrea Lodi

In this paper, we focus on fully connected deep neural networks utilizing the Rectified Linear Unit (ReLU) activation function for nonparametric estimation. We derive non-asymptotic bounds that lead to convergence rates, addressing both…

While suitably scaled CNNs with Gaussian initialization are known to converge to Gaussian processes as the number of channels diverges, little is known beyond this Gaussian limit. We establish a large deviation principle (LDP) for…

Probability · Mathematics 2026-03-09 Federico Bassetti , Vassili De Palma , Lucia Ladelli