English
Related papers

Related papers: GLU Variants Improve Transformer

200 papers

Rectified Linear Units (ReLUs) have been shown to ameliorate the vanishing gradient problem, allow for efficient backpropagation, and empirically promote sparsity in the learned parameters. They have led to state-of-the-art results in a…

Machine Learning · Computer Science 2016-05-30 Xingyuan Pan , Vivek Srikumar

Feed-forward networks can be interpreted as mappings with linear decision surfaces at the level of the last layer. We investigate how the tangent space of the network can be exploited to refine the decision in case of ReLU (Rectified Linear…

Machine Learning · Computer Science 2021-10-27 Dániel Rácz , Bálint Daróczy

Activation functions are fundamental to deep neural networks, governing gradient flow, optimization stability, and representational capacity. Within historic deep architectures, while ReLU has been the dominant choice for the activation…

Machine Learning · Computer Science 2026-03-10 Mingi Kang , Zai Yang , Jeova Farias Sales Rocha Neto

The paper proposes representation functionals in a dual paradigm where learning jointly concerns both linear convolutional weights and parametric forms of nonlinear activation functions. The nonlinear forms proposed for performing the…

Information Retrieval · Computer Science 2021-02-08 Abdourrahmane Mahamane Atto , Sylvie Galichet , Dominique Pastor , Nicolas Méger

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

Selecting the most suitable activation function is a critical factor in the effectiveness of deep learning models, as it influences their learning capacity, stability, and computational efficiency. In recent years, the Gaussian Error Linear…

Machine Learning · Computer Science 2023-08-02 Minhyeok Lee

Traffic flow prediction is an essential task in constructing smart cities and is a typical Multivariate Time Series (MTS) Problem. Recent research has abandoned Gated Recurrent Units (GRU) and utilized dilated convolutions or temporal…

Artificial Intelligence · Computer Science 2024-04-19 Wenfeng Zhang , Xin Li , Anqi Li , Xiaoting Huang , Ti Wang , Honglei Gao

We study layered neural networks of rectified linear units (ReLU) in a modelling framework for stochastic training processes. The comparison with sigmoidal activation functions is in the center of interest. We compute typical learning…

Machine Learning · Computer Science 2020-11-13 Elisa Oostwal , Michiel Straat , Michael Biehl

Transformers have improved drastically the performance of natural language processing (NLP) and computer vision applications. The computation of transformers involves matrix multiplications and non-linear activation functions such as…

Hardware Architecture · Computer Science 2024-02-19 Christodoulos Peltekis , Kosmas Alexandridis , Giorgos Dimitrakopoulos

Recent work has shown that purely quadratic functions can replace MLPs in transformers with no significant loss in performance, while enabling new methods of interpretability based on linear algebra. In this work, we theoretically derive…

Machine Learning · Computer Science 2025-02-04 Nora Belrose , Alice Rigg

We propose a novel activation function that implements piece-wise orthogonal non-linear mappings based on permutations. It is straightforward to implement, and very computationally efficient, also it has little memory requirements. We…

Neural and Evolutionary Computing · Computer Science 2017-02-02 Artem Chernodub , Dimitri Nowicki

We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences. First, we propose a simple layer named gated attention unit, which allows the use of a weaker single-head attention…

Machine Learning · Computer Science 2022-06-28 Weizhe Hua , Zihang Dai , Hanxiao Liu , Quoc V. Le

Recurrent neural networks with various types of hidden units have been used to solve a diverse range of problems involving sequence data. Two of the most recent proposals, gated recurrent units (GRU) and minimal gated units (MGU), have…

Neural and Evolutionary Computing · Computer Science 2017-01-13 Joel Heck , Fathi M. Salem

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

The Rectified Linear Unit is currently a state-of-the-art activation function in deep convolutional neural networks. To combat ReLU's dying neuron problem, we propose the Parametric Variational Linear Unit (PVLU), which adds a sinusoidal…

Computer Vision and Pattern Recognition · Computer Science 2021-12-20 Aarush Gupta , Shikhar Ahuja

Gated recurrent neural networks have achieved remarkable results in the analysis of sequential data. Inside these networks, gates are used to control the flow of information, allowing to model even very long-term dependencies in the data.…

Neural and Evolutionary Computing · Computer Science 2018-07-12 Simone Scardapane , Steven Van Vaerenbergh , Danilo Comminiello , Simone Totaro , Aurelio Uncini

Rectified linear unit (ReLU) is a widely used activation function for deep convolutional neural networks. However, because of the zero-hard rectification, ReLU networks miss the benefits from negative values. In this paper, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2018-01-30 Suo Qiu , Xiangmin Xu , Bolun Cai

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

Activation functions play a critical role in deep neural networks by shaping gradient flow, optimization stability, and generalization. While ReLU remains widely used due to its simplicity, it suffers from gradient sparsity and dead-neuron…

Machine Learning · Computer Science 2025-12-03 Ashkan Shakarami , Yousef Yeganeh , Azade Farshad , Lorenzo Nicolè , Stefano Ghidoni , Nassir Navab

Recently recurrent neural networks (RNN) has been very successful in handling sequence data. However, understanding RNN and finding the best practices for RNN is a difficult task, partly because there are many competing and complex hidden…

Neural and Evolutionary Computing · Computer Science 2016-04-01 Guo-Bing Zhou , Jianxin Wu , Chen-Lin Zhang , Zhi-Hua Zhou