English
Related papers

Related papers: SERF: Towards better training of deep neural netwo…

200 papers

Successive linear transforms followed by nonlinear "activation" functions can approximate nonlinear functions to arbitrary precision given sufficient layers. The number of necessary layers is dependent on, in part, by the nature of the…

Neural and Evolutionary Computing · Computer Science 2018-09-26 Andrei Nicolae

In recent years, functional neural networks have been proposed and studied in order to approximate nonlinear continuous functionals defined on $L^p([-1, 1]^s)$ for integers $s\ge1$ and $1\le p<\infty$. However, their theoretical properties…

Machine Learning · Statistics 2023-04-11 Linhao Song , Jun Fan , Di-Rong Chen , Ding-Xuan Zhou

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

The softmax activation function plays a crucial role in the success of large language models (LLMs), particularly in the self-attention mechanism of the widely adopted Transformer architecture. However, the underlying learning dynamics that…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Yingyu Liang , Zhenmei Shi , Zhao Song

The reason behind CNNs capability to learn high-dimensional complex features from the images is the non-linearity introduced by the activation function. Several advanced activation functions have been discovered to improve the training…

Machine Learning · Computer Science 2022-11-15 Jeevanshi Sharma

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

Lipschitz-constrained neural networks have many applications in machine learning. Since designing and training expressive Lipschitz-constrained networks is very challenging, there is a need for improved methods and a better theoretical…

Machine Learning · Computer Science 2022-04-14 Sebastian Neumayer , Alexis Goujon , Pakshal Bohra , Michael Unser

The choice of activation function plays a critical role in neural networks, yet most architectures still rely on fixed, uniform activation functions across all neurons. We introduce SmartMixed, a two-phase training strategy that allows…

Machine Learning · Computer Science 2025-11-03 Amin Omidvar

The loss function used to train a neural network is strongly connected to its output layer from a statistical point of view. This technical report analyzes common activation functions for a neural network output layer, like linear, sigmoid,…

Machine Learning · Computer Science 2025-11-10 Fernando Berzal

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

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

Deep learning, in the form of artificial neural networks, has achieved remarkable practical success in recent years, for a variety of difficult machine learning applications. However, a theoretical explanation for this remains a major open…

Machine Learning · Computer Science 2016-06-15 Itay Safran , Ohad Shamir

Inducing and leveraging sparse activations during training and inference is a promising avenue for improving the computational efficiency of deep networks, which is increasingly important as network sizes continue to grow and their…

Machine Learning · Computer Science 2024-02-27 Ilan Price , Nicholas Daultry Ball , Samuel C. H. Lam , Adam C. Jones , Jared Tanner

Rectified Linear Units (ReLU) are the default choice for activation functions in deep neural networks. While they demonstrate excellent empirical performance, ReLU activations can fall victim to the dead neuron problem. In these cases, the…

Machine Learning · Computer Science 2023-02-14 Tim Whitaker , Darrell Whitley

A pivotal aspect in the design of neural networks lies in selecting activation functions, crucial for introducing nonlinear structures that capture intricate input-output patterns. While the effectiveness of adaptive or trainable activation…

Machine Learning · Computer Science 2024-08-06 Farhad Pourkamali-Anaraki , Tahamina Nasrin , Robert E. Jensen , Amy M. Peterson , Christopher J. Hansen

In recent years, deep neural networks (DNNs) achieved unprecedented performance in many low-level vision tasks. However, state-of-the-art results are typically achieved by very deep networks, which can reach tens of layers with tens of…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Idan Kligvasser , Tamar Rott Shaham , Tomer Michaeli

We study the expressivity of deep neural networks. Measuring a network's complexity by its number of connections or by its number of neurons, we consider the class of functions for which the error of best approximation with networks of a…

Functional Analysis · Mathematics 2020-07-20 Rémi Gribonval , Gitta Kutyniok , Morten Nielsen , Felix Voigtlaender

Motivated by the growing theoretical understanding of neural networks that employ the Rectified Linear Unit (ReLU) as their activation function, we revisit the use of ReLU activation functions for learning implicit neural representations…

Image and Video Processing · Electrical Eng. & Systems 2024-08-05 Joseph Shenouda , Yamin Zhou , Robert D. Nowak

The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in Natural Language Processing (NLP). Initial graph prompt…

Machine Learning · Computer Science 2025-01-20 Jiapeng Zhu , Zichen Ding , Jianxiang Yu , Jiaqi Tan , Xiang Li , Weining Qian

Activation functions play a decisive role in determining the capacity of Deep Neural Networks as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions…

Computer Vision and Pattern Recognition · Computer Science 2023-05-31 Jamshaid Ul Rahman , Faiza Makhdoom , Dianchen Lu