医学中的 Kolmogorov Arnold Network 自编码器
Kolmogorov Arnold Network Autoencoder in Medicine
AI总结：
本文针对心脏听诊音频信号，系统比较线性、卷积和变分自编码器与其参数更少或相当的 KAN 版本在重建、生成、去噪、修复及异常检测任务上的表现。
摘要：
诸如多层感知机（MLP）和卷积块之类的深度学习神经网络架构，在当今研究进展中仍发挥着关键作用。从拓扑角度看，这些架构可以表示为图：我们在图中学习与节点相关的函数，而固定的边将信息从输入传递到输出。最近一项工作提出了名为 Kolmogorov Arnold Networks（KAN）的新架构，报告了将可学习激活函数置于神经网络边上如何在多种场景中带来更好性能。多项研究正聚焦于优化 KAN 架构，加入 dropout 正则化、自编码器（AE）、模型基准测试等重要特性，以及同样重要的 KAN Convolutional Network（KCN），后者通过 KAN 学习引入了矩阵卷积。本研究旨在对多个版本的原始 AE（如线性、卷积和变分 AE）与其 Kolmogorov-Arnold 对应模型进行基准比较，后者具有相同或更少的参数量。研究以心脏科信号作为模型输入，共考察五项不同的经典 AE 任务：重建、生成、去噪、修复和异常检测。所提出的实验使用医学数据集 AbnormalHeartbeat，其中包含通过听诊器获得的音频信号。
英文摘要：
Deep learning neural networks architectures such Multi Layer Perceptrons (MLP) and Convolutional blocks still play a crucial role in nowadays research advancements. From a topological point of view, these architecture may be represented as graphs in which we learn the functions related to the nodes while fixed edges convey the information from the input to the output. A recent work introduced a new architecture called Kolmogorov Arnold Networks (KAN) that reports how putting learnable activation functions on the edges of the neural network leads to better performances in multiple scenarios. Multiple studies are focusing on optimizing the KAN architecture by adding important features such as dropout regularization, Autoencoders (AE), model benchmarking and last, but not least, the KAN Convolutional Network (KCN) that introduced matrix convolution with KANs learning. This study aims to benchmark multiple versions of vanilla AEs (such as Linear, Convolutional and Variational) against their Kolmogorov-Arnold counterparts that have same or less number of parameters. Using cardiological signals as model input, a total of five different classic AE tasks were studied: reconstruction, generation, denoising, inpainting and anomaly detection. The proposed experiments uses a medical dataset \textit{AbnormalHeartbeat} that contains audio signals obtained from the stethoscope.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
