English
Related papers

Related papers: GLU Variants Improve Transformer

200 papers

A big convergence of model architectures across language, vision, speech, and multimodal is emerging. However, under the same name "Transformers", the above areas use different implementations for better performance, e.g., Post-LayerNorm…

For many machine learning applications, a common input representation is a spectrogram. The underlying representation for a spectrogram is a short time Fourier transform (STFT) which gives complex values. The spectrogram uses the magnitude…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-28 Les Atlas , Nicholas Rasmussen , Felix Schwock , Mert Pilanci

Inversion-based feedforward control relies on an accurate model that describes the inverse system dynamics. The gated recurrent unit (GRU), which is a recent architecture in recurrent neural networks, is a strong candidate for obtaining…

Systems and Control · Electrical Eng. & Systems 2025-07-21 Mingdao Lin , Max Bolderman , Mircea Lazar

Flow-based generative models (Dinh et al., 2014) are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and synthesis. In this…

Machine Learning · Statistics 2018-07-11 Diederik P. Kingma , Prafulla Dhariwal

Transformers have surpassed RNNs in popularity due to their superior abilities in parallel training and long-term dependency modeling. Recently, there has been a renewed interest in using linear RNNs for efficient sequence modeling. These…

Computation and Language · Computer Science 2023-11-09 Zhen Qin , Songlin Yang , Yiran Zhong

Transformer-based models have demonstrated remarkable in-context learning capabilities, prompting extensive research into its underlying mechanisms. Recent studies have suggested that Transformers can implement first-order optimization…

Machine Learning · Computer Science 2024-03-06 Angeliki Giannou , Liu Yang , Tianhao Wang , Dimitris Papailiopoulos , Jason D. Lee

Equivariant neural networks are neural networks with symmetry. Motivated by the theory of group representations, we decompose the layers of an equivariant neural network into simple representations. The nonlinear activation functions lead…

Machine Learning · Computer Science 2026-03-30 Joel Gibson , Daniel Tubbenhauer , Geordie Williamson

Transformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple network architecture, gMLP, based on MLPs with gating, and…

Machine Learning · Computer Science 2021-06-03 Hanxiao Liu , Zihang Dai , David R. So , Quoc V. Le

This paper proposes a novel and insightful activation method termed FPLUS, which exploits mathematical power function with polar signs in form. It is enlightened by common inverse operation while endowed with an intuitive meaning of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Boxi Duan

The application of the deep learning model in classification plays an important role in the accurate detection of the target objects. However, the accuracy is affected by the activation function in the hidden and output layer. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-05-22 Md. Mehedi Hasan , Md. Ali Hossain , Azmain Yakin Srizon , Abu Sayeed

Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-27 Zhanzhan Cheng , Yunlu Xu , Mingjian Cheng , Yu Qiao , Shiliang Pu , Yi Niu , Fei Wu

Complex numbers have long been favoured for digital signal processing, yet complex representations rarely appear in deep learning architectures. RNNs, widely used to process time series and sequence information, could greatly benefit from…

Machine Learning · Computer Science 2018-10-30 Moritz Wolter , Angela Yao

We consider building predictors when the data have missing values. We study the seemingly-simple case where the target to predict is a linear function of the fully-observed data and we show that, in the presence of missing values, the…

Machine Learning · Computer Science 2020-07-02 Marine Le Morvan , Nicolas Prost , Julie Josse , Erwan Scornet , Gaël Varoquaux

In this work, we propose a novel recurrent neural network (RNN) architecture. The proposed RNN, gated-feedback RNN (GF-RNN), extends the existing approach of stacking multiple recurrent layers by allowing and controlling signals flowing…

Neural and Evolutionary Computing · Computer Science 2015-06-18 Junyoung Chung , Caglar Gulcehre , Kyunghyun Cho , Yoshua Bengio

This paper investigates the ability of finite samples to identify two-layer irreducible shallow networks with various nonlinear activation functions, including rectified linear units (ReLU) and analytic functions such as the logistic…

Machine Learning · Computer Science 2025-03-18 Yu Xia , Zhiqiang Xu

Activation function is crucial to the recent successes of deep neural networks. In this paper, we first propose a new activation function, Multiple Parametric Exponential Linear Units (MPELU), aiming to generalize and unify the rectified…

Computer Vision and Pattern Recognition · Computer Science 2017-01-18 Yang Li , Chunxiao Fan , Yong Li , Qiong Wu , Yue Ming

Artificial neural networks usually consist of successive linear multiply-accumulate operations and nonlinear activation functions. However, most optical neural networks only achieve the linear operation in the optical domain, while the…

Optics · Physics 2023-11-03 Guanting Liu , Yiwei Shen , Ruiqian Li , Jingyi Yu , Xuming He , Cheng Wang

Node tokenized graph Transformers (GTs) have shown promising performance in node classification. The generation of token sequences is the key module in existing tokenized GTs which transforms the input graph into token sequences,…

Machine Learning · Computer Science 2025-02-13 Jinsong Chen , Chenyang Li , GaiChao Li , John E. Hopcroft , Kun He

There is an increasing interest in the application of deep learning architectures to tabular data. One of the state-of-the-art solutions is TabTransformer which incorporates an attention mechanism to better track relationships between…

Machine Learning · Computer Science 2022-01-04 Radostin Cholakov , Todor Kolev

Transformers have been designed for channel acquisition tasks such as channel prediction and other tasks such as precoding, while graph neural networks (GNNs) have been demonstrated to be efficient for learning a multitude of communication…

Signal Processing · Electrical Eng. & Systems 2025-03-06 Yuxuan Duan , Jia Guo , Chenyang Yang