English
Related papers

Related papers: Shifting Mean Activation Towards Zero with Bipolar…

200 papers

Activation functions are essential for deep learning methods to learn and perform complex tasks such as image classification. Rectified Linear Unit (ReLU) has been widely used and become the default activation function across the deep…

Neural and Evolutionary Computing · Computer Science 2018-12-18 Hock Hung Chieng , Noorhaniza Wahid , Pauline Ong , Sai Raj Kishore Perla

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 popular and useful in many fields, but they have the problem of giving high confidence responses for examples that are away from the training data. This makes the neural networks very confident in their prediction while…

Machine Learning · Computer Science 2024-10-15 Adrian Barbu , Hongyu Mou

Batch Normalization (BN) uses mini-batch statistics to normalize the activations during training, introducing dependence between mini-batch elements. This dependency can hurt the performance if the mini-batch size is too small, or if the…

Machine Learning · Computer Science 2020-04-02 Saurabh Singh , Shankar Krishnan

Initializing the weights and the biases is a key part of the training process of a neural network. Unlike the subsequent optimization phase, however, the initialization phase has gained only limited attention in the literature. In this…

Machine Learning · Computer Science 2019-09-06 Ingo Steinwart

In this paper, we study 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While efficient, the lacking of representational capability and the training difficulty impede 1-bit CNNs from…

Computer Vision and Pattern Recognition · Computer Science 2019-09-05 Zechun Liu , Wenhan Luo , Baoyuan Wu , Xin Yang , Wei Liu , Kwang-Ting Cheng

Power Normalizations (PN) are very useful non-linear operators in the context of Bag-of-Words data representations as they tackle problems such as feature imbalance. In this paper, we reconsider these operators in the deep learning setup by…

Computer Vision and Pattern Recognition · Computer Science 2018-06-26 Piotr Koniusz , Hongguang Zhang , Fatih Porikli

Neural networks are more expressive when they have multiple layers. In turn, conventional training methods are only successful if the depth does not lead to numerical issues such as exploding or vanishing gradients, which occur less…

Machine Learning · Computer Science 2022-06-07 Carles Riera , Camilo Rey , Thiago Serra , Eloi Puertas , Oriol Pujol

A simple approach is proposed to obtain complexity controls for neural networks with general activation functions. The approach is motivated by approximating the general activation functions with one-dimensional ReLU networks, which reduces…

Machine Learning · Computer Science 2020-09-15 Zhong Li , Chao Ma , Lei Wu

Continual learning entails learning a sequence of tasks and balancing their knowledge appropriately. With limited access to old training samples, much of the current work in deep neural networks has focused on overcoming catastrophic…

Machine Learning · Computer Science 2023-10-16 Yilin Lyu , Liyuan Wang , Xingxing Zhang , Zicheng Sun , Hang Su , Jun Zhu , Liping Jing

The Rectified Linear Unit (ReLU) is a foundational activation function in artficial neural networks. Recent literature frequently misattributes its origin to the 2018 (initial) version of this paper, which exclusively investigated ReLU at…

Neural and Evolutionary Computing · Computer Science 2026-04-15 Abien Fred Agarap

In this paper, we consider one dimensional (shallow) ReLU neural networks in which weights are chosen randomly and only the terminal layer is trained. First, we mathematically show that for such networks L2-regularized regression…

Machine Learning · Computer Science 2023-10-05 Jakob Heiss , Josef Teichmann , Hanna Wutte

Gradient-based neural network training traditionally enforces symmetry between forward and backward propagation, requiring activation functions to be differentiable (or sub-differentiable) and strictly monotonic in certain regions to…

Neural and Evolutionary Computing · Computer Science 2025-09-10 Luigi Troiano , Francesco Gissi , Vincenzo Benedetto , Genny Tortora

In this paper, we investigate the relationship between deep neural networks (DNN) with rectified linear unit (ReLU) function as the activation function and continuous piecewise linear (CPWL) functions, especially CPWL functions from the…

Numerical Analysis · Mathematics 2020-06-02 Juncai He , Lin Li , Jinchao Xu , Chunyue Zheng

ReLU, a commonly used activation function in deep neural networks, is prone to the issue of "Dying ReLU". Several enhanced versions, such as ELU, SeLU, and Swish, have been introduced and are considered to be less commonly utilized.…

Machine Learning · Computer Science 2024-07-12 Jamshaid Ul Rahman , Rubiqa Zulfiqar , Asad Khan , Nimra

Deep Neural Networks (DNNs) provide state-of-the-art solutions in several difficult machine perceptual tasks. However, their performance relies on the availability of a large set of labeled training data, which limits the breadth of their…

Machine Learning · Computer Science 2018-03-01 Randall Balestriero , Herve Glotin , Richard Baraniuk

Recurrent neural networks (RNN) are used in many real-world text and speech applications. They include complex modules such as recurrence, exponential-based activation, gate interaction, unfoldable normalization, bi-directional dependence,…

Machine Learning · Computer Science 2022-02-16 Eyyüb Sari , Vanessa Courville , Vahid Partovi Nia

The ability to selectively remove knowledge from LLMs is highly desirable. However, existing methods often struggle with balancing unlearning efficacy and retain model utility, and lack controllability at inference time to emulate base…

Machine Learning · Computer Science 2025-10-09 William F. Shen , Xinchi Qiu , Meghdad Kurmanji , Alex Iacob , Lorenzo Sani , Yihong Chen , Nicola Cancedda , Nicholas D. Lane

Neural networks are usually trained with different variants of gradient descent based optimization algorithms such as stochastic gradient descent or the Adam optimizer. Recent theoretical work states that the critical points (where the…

Machine Learning · Computer Science 2024-10-15 Adrian Barbu

In this paper, it is demonstrated through a case study that multilayer feedforward neural networks activated by ReLU functions can in principle be trained iteratively with Mixed Integer Linear Programs (MILPs) as follows. Weights are…

Machine Learning · Computer Science 2021-04-12 Steffen Goebbels