English
Related papers

Related papers: DropKAN: Regularizing KANs by masking post-activat…

200 papers

Deeply stacked KANs are practically impossible due to high training difficulties and substantial memory requirements. Consequently, existing studies can only incorporate few KAN layers, hindering the comprehensive exploration of KANs. This…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Xingyu Qiu , Xinghua Ma , Dong Liang , Gongning Luo , Wei Wang , Kuanquan Wang , Shuo Li

In this paper, we introduce DropHead, a structured dropout method specifically designed for regularizing the multi-head attention mechanism, which is a key component of transformer, a state-of-the-art model for various NLP tasks. In…

Computation and Language · Computer Science 2020-11-03 Wangchunshu Zhou , Tao Ge , Ke Xu , Furu Wei , Ming Zhou

One major challenge in training Deep Neural Networks is preventing overfitting. Many techniques such as data augmentation and novel regularizers such as Dropout have been proposed to prevent overfitting without requiring a massive amount of…

Machine Learning · Computer Science 2016-06-13 Michael Cogswell , Faruk Ahmed , Ross Girshick , Larry Zitnick , Dhruv Batra

Time series anomaly detection (TSAD) underpins real-time monitoring in cloud services and web systems, allowing rapid identification of anomalies to prevent costly failures. Most TSAD methods driven by forecasting models tend to overfit by…

Machine Learning · Computer Science 2026-05-29 Quan Zhou , Changhua Pei , Fei Sun , Jing Han , Zhengwei Gao , Dan Pei , Haiming Zhang , Gaogang Xie , Jianhui Li

Kolmogorov-Arnold Networks (KANs) have recently emerged as a powerful architecture for various machine learning applications. However, their unique structure raises significant concerns regarding their computational overhead. Existing…

Machine Learning · Computer Science 2026-04-07 Bilal Khalid , Pedro Freire , Sergei K. Turitsyn , Jaroslaw E. Prilepsky

Kolmogorov-Arnold Networks (KANs) have recently shown promise for solving partial differential equations (PDEs). Yet their original formulation is computationally and memory intensive, motivating the introduction of Chebyshev Type-I-based…

Machine Learning · Computer Science 2026-01-19 Hangwei Zhang , Zhimu Huang , Yan Wang

Kolmogorov-Arnold Networks (KANs) have garnered significant attention for their promise of improved parameter efficiency and explainability compared to traditional Deep Neural Networks (DNNs). KANs' key innovation lies in the use of…

Hardware Architecture · Computer Science 2025-12-02 Sohaib Errabii , Olivier Sentieys , Marcello Traiola

This paper presents a novel approach to recurrent neural network (RNN) regularization. Differently from the widely adopted dropout method, which is applied to \textit{forward} connections of feed-forward architectures or RNNs, we propose to…

Computation and Language · Computer Science 2016-08-08 Stanislau Semeniuta , Aliaksei Severyn , Erhardt Barth

In traditional neural network architectures, a multilayer perceptron (MLP) is typically employed as a classification block following the feature extraction stage. However, the Kolmogorov-Arnold Network (KAN) presents a promising alternative…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Valeriy Lobanov , Nikita Firsov , Evgeny Myasnikov , Roman Khabibullin , Artem Nikonorov

Catastrophic forgetting remains the central obstacle in continual learning (CL): parameters shared across tasks interfere with one another, and existing regularization methods such as EWC and SI apply uniform penalties without awareness of…

Machine Learning · Computer Science 2026-05-13 Minjong Cheon

Objective: This paper investigates the potential of learnable activation functions in Kolmogorov-Arnold Networks (KANs) for personalized control in a lower-limb prosthesis. In addition, user-specific vs. pooled training data is evaluated to…

Machine Learning · Computer Science 2025-05-15 SeyedMojtaba Mohasel , Alireza Afzal Aghaei , Corey Pew

We develop a method for multifidelity Kolmogorov-Arnold networks (KANs), which use a low-fidelity model along with a small amount of high-fidelity data to train a model for the high-fidelity data accurately. Multifidelity KANs (MFKANs)…

Machine Learning · Computer Science 2024-10-22 Amanda A. Howard , Bruno Jacob , Panos Stinis

Dropout is a widely-used regularization technique, often required to obtain state-of-the-art for a number of architectures. This work demonstrates that dropout introduces two distinct but entangled regularization effects: an explicit effect…

Machine Learning · Computer Science 2020-10-16 Colin Wei , Sham Kakade , Tengyu Ma

Dropout, a simple and effective way to train deep neural networks, has led to a number of impressive empirical successes and spawned many recent theoretical investigations. However, the gap between dropout's training and inference phases,…

Machine Learning · Computer Science 2017-02-17 Xuezhe Ma , Yingkai Gao , Zhiting Hu , Yaoliang Yu , Yuntian Deng , Eduard Hovy

Hypergraph representation learning has garnered increasing attention across various domains due to its capability to model high-order relationships. Traditional methods often rely on hypergraph neural networks (HNNs) employing message…

Machine Learning · Computer Science 2025-03-18 Xiangfei Fang , Boying Wang , Chengying Huan , Shaonan Ma , Heng Zhang , Chen Zhao

Kolmogorov-Arnold Networks (KANs) offer a promising path toward interpretable machine learning: their learnable activations can be studied individually, while collectively fitting complex data accurately. In practice, however, trained…

Machine Learning · Computer Science 2025-12-10 James Bagrow , Josh Bongard

Dropout is a widely used regularization technique in deep learning, but its effects are typically realized through stochastic masking rather than explicit optimization objectives. We propose a deterministic formulation that expresses…

Machine Learning · Computer Science 2026-04-23 Vidhi Agrawal , Illia Oleksiienko , Alexandros Iosifidis

Multilayer Perceptron (MLP), as a simple yet powerful model, continues to be widely used in classification and regression tasks. However, traditional MLPs often struggle to efficiently capture nonlinear relationships in load data when…

Machine Learning · Computer Science 2025-05-13 Yizhou Ma , Zhuoqin Yang , Luis-Daniel Ibáñez

The modern digital engineering design often requires costly repeated simulations for different scenarios. The prediction capability of neural networks (NNs) makes them suitable surrogates for providing design insights. However, only a few…

Computational Engineering, Finance, and Science · Computer Science 2024-08-08 Diab W. Abueidda , Panos Pantidis , Mostafa E. Mobasher

Multilayer Perceptrons (MLPs) have long been a cornerstone in deep learning, known for their capacity to model complex relationships. Recently, Kolmogorov-Arnold Networks (KANs) have emerged as a compelling alternative, utilizing highly…

Machine Learning · Computer Science 2024-09-17 Farhad Pourkamali-Anaraki