用于异常检测模型鲁棒训练的简洁对数损失函数
Concise Logarithmic Loss Function for Robust Training of Anomaly Detection Model
AI总结：
本文提出对数均方误差（LMSE）损失函数，用于更稳定地训练异常检测模型，并通过数学分析、反向传播可视化、损失收敛和检测性能比较证明其优于传统均方误差（MSE），且有望推广至一般生成式神经网络。
摘要：
近年来，基于深度学习的算法被广泛采用，因为其优势在于能够在没有或仅有极少任务领域知识的情况下建立异常检测模型。相反，为了更稳定地训练人工神经网络，最好定义合适的神经网络结构或损失函数。在训练异常检测模型时，均方误差（MSE）函数被广泛采用。另一方面，本文提出了一种新的损失函数，即对数均方误差（LMSE），以更稳定地训练神经网络。本研究涵盖了多种比较，包括数学比较、反向传播中微分域的可视化、训练过程中的损失收敛以及异常检测性能。从总体上看，LMSE在损失收敛的强健性和异常检测性能方面优于现有的MSE函数。预计LMSE函数不仅适用于训练异常检测模型，还适用于训练一般的生成式神经网络。
英文摘要：
Recently, deep learning-based algorithms are widely adopted due to the advantage of being able to establish anomaly detection models without or with minimal domain knowledge of the task. Instead, to train the artificial neural network more stable, it should be better to define the appropriate neural network structure or the loss function. For the training anomaly detection model, the mean squared error (MSE) function is adopted widely. On the other hand, the novel loss function, logarithmic mean squared error (LMSE), is proposed in this paper to train the neural network more stable. This study covers a variety of comparisons from mathematical comparisons, visualization in the differential domain for backpropagation, loss convergence in the training process, and anomaly detection performance. In an overall view, LMSE is superior to the existing MSE function in terms of strongness of loss convergence, anomaly detection performance. The LMSE function is expected to be applicable for training not only the anomaly detection model but also the general generative neural network.
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。
