English
Related papers

Related papers: Complex Clipping for Improved Generalization in Ma…

200 papers

In this work, we propose to train a deep neural network by distributed optimization over a graph. Two nonlinear functions are considered: the rectified linear unit (ReLU) and a linear unit with both lower and upper cutoffs (DCutLU). The…

Machine Learning · Computer Science 2017-06-20 Guoqiang Zhang , W. Bastiaan Kleijn

Activation in deep neural networks is fundamental to achieving non-linear mappings. Traditional studies mainly focus on finding fixed activations for a particular set of learning tasks or model architectures. The research on flexible…

Neural and Evolutionary Computing · Computer Science 2020-08-20 Renlong Jie , Junbin Gao , Andrey Vasnev , Min-ngoc Tran

Linear recurrent neural networks, such as State Space Models (SSMs) and Linear Recurrent Units (LRUs), have recently shown state-of-the-art performance on long sequence modelling benchmarks. Despite their success, their empirical…

Machine Learning · Computer Science 2024-10-08 Kai Biegun , Rares Dolga , Jake Cunningham , David Barber

As a widely used non-linear activation, Rectified Linear Unit (ReLU) separates noise and signal in a feature map by learning a threshold or bias. However, we argue that the classification of noise and signal not only depends on the…

Computer Vision and Pattern Recognition · Computer Science 2016-04-05 Hongyang Li , Wanli Ouyang , Xiaogang Wang

Despite their ability to represent highly expressive functions, deep learning models seem to find simple solutions that generalize surprisingly well. Spectral bias -- the tendency of neural networks to prioritize learning low frequency…

Machine Learning · Computer Science 2022-09-30 Sara Fridovich-Keil , Raphael Gontijo-Lopes , Rebecca Roelofs

Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation (NMT). While sentences are usually converted into unique subword sequences, subword segmentation is potentially ambiguous and…

Computation and Language · Computer Science 2018-05-01 Taku Kudo

We consider deep feedforward neural networks with rectified linear units from a signal processing perspective. In this view, such representations mark the transition from using a single (data-driven) linear representation to utilizing a…

Machine Learning · Computer Science 2019-04-01 Andreas Heinecke , Wen-Liang Hwang

In this work, we provide a characterization of the feature-learning process in two-layer ReLU networks trained by gradient descent on the logistic loss following random initialization. We consider data with binary labels that are generated…

Machine Learning · Computer Science 2023-09-15 Spencer Frei , Niladri S. Chatterji , Peter L. Bartlett

We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis and show that it improves the sample efficiency of both state-based and image-based RL. We perform infinite-width analysis of…

Machine Learning · Computer Science 2021-12-07 Alexander C. Li , Deepak Pathak

Most complex machine learning and modelling techniques are prone to over-fitting and may subsequently generalise poorly to future data. Artificial neural networks are no different in this regard and, despite having a level of implicit…

Machine Learning · Statistics 2022-05-26 Vincent Szolnoky , Viktor Andersson , Balazs Kulcsar , Rebecka Jörnsten

Representation Fine-tuning (ReFT), a recently proposed Parameter-Efficient Fine-Tuning (PEFT) method, has attracted widespread attention for significantly improving parameter efficiency by editing representation space alone. In this work,…

Computation and Language · Computer Science 2025-07-15 Chenxi Huang , Shaotian Yan , Liang Xie , Binbin Lin , Sinan Fan , Yue Xin , Deng Cai , Chen Shen , Jieping Ye

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

Deep learning algorithms -- typically consisting of a class of deep artificial neural networks (ANNs) trained by a stochastic gradient descent (SGD) optimization method -- are nowadays an integral part in many areas of science, industry,…

Machine Learning · Computer Science 2025-01-28 Steffen Dereich , Thang Do , Arnulf Jentzen , Frederic Weber

We introduce the "exponential linear unit" (ELU) which speeds up learning in deep neural networks and leads to higher classification accuracies. Like rectified linear units (ReLUs), leaky ReLUs (LReLUs) and parametrized ReLUs (PReLUs), ELUs…

Machine Learning · Computer Science 2016-02-23 Djork-Arné Clevert , Thomas Unterthiner , Sepp Hochreiter

ReLU neural networks trained as surrogate models can be embedded exactly in mixed-integer linear programs (MILPs), enabling global optimization over the learned function. The tractability of the resulting MILP depends on structural…

Optimization and Control · Mathematics 2026-04-27 Calvin Tsay

During the inversion of discrete linear systems noise in data can be amplified and result in meaningless solutions. To combat this effect, characteristics of solutions that are considered desirable are mathematically implemented during…

Numerical Analysis · Mathematics 2023-02-07 Michael J. Byrne , Rosemary A. Renaut

Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that…

Computation and Language · Computer Science 2024-12-10 Tingyu Xia , Bowen Yu , Kai Dang , An Yang , Yuan Wu , Yuan Tian , Yi Chang , Junyang Lin

Traditional Convolutional Neural Networks (CNNs) typically use the same activation function (usually ReLU) for all neurons with non-linear mapping operations. For example, the deep convolutional architecture Inception-v4 uses ReLU. To…

Computer Vision and Pattern Recognition · Computer Science 2018-05-31 Luna M. Zhang

Vision-language alignment in multi-modal large language models (MLLMs) relies on supervised fine-tuning (SFT) or reinforcement learning (RL). To align multi-modal large language models (MLLMs) in the post-training stage, supervised…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Xin Jin , Siyuan Li , Siyong Jian , Kai Yu , Huan Wang

In recent years, point cloud upsampling has been widely applied in tasks such as 3D reconstruction and object recognition. This study proposed a novel framework, ReLPU, which enhances upsampling performance by explicitly learning from both…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Tongxu Zhang , Bei Wang