This paper proposes an improved design of the perceptron unit to mitigate the vanishing gradient problem. This nuisance appears when training deep multilayer perceptron networks with bounded activation functions. The new neuron design, named auto-rotating perceptron (ARP), has a mechanism to ensure that the node always operates in the dynamic region of the activation function, by avoiding saturation of the perceptron. The proposed method does not change the inference structure learned at each neuron. We test the effect of using ARP units in some network architectures which use the sigmoid activation function. The results support our hypothesis that neural networks with ARP units can achieve better learning performance than equivalent models with classic perceptrons.
ECO-AMLP: A Decision Support System using an Enhanced Class Outlier with Automatic Multilayer Perceptron for Diabetes Prediction
National University of Sciences & Technology（国家科学与技术大学）；Manchester Metropolitan University（曼彻斯特城市大学）
随着先进的数据分析技术，为疾病预测提供更准确的决策支持系统的努力正在增加。世界卫生组织（WHO）的调查表明，糖尿病患者和相关死亡人数每年都在大幅增加。糖尿病的早期诊断是研究人员和从业人员的主要关注点。本文提出了一个应用\textit{Automatic Multilayer Perceptron }，\textit{ }结合离群检测方法\textit{Enhanced Class Outlier Detection using distance based algorithm }，创建一个预测框架命名为增强类离群自动多层感知器（ECO-AMLP）。一系列的实验进行公开的皮马印度糖尿病数据集比较ECO-AMLP与其他个人分类器以及集成为基础的方法。与其他预处理和分类技术相比，我们框架中使用的离群值技术得到了更好的结果。最后，将结果与文献中报道的其他最先进的方法进行比较，预测PIDD糖尿病的准确性为88.7%，优于所有其他报道的研究。
Constructing the Matrix Multilayer Perceptron and its Application to the VAE
Uppsala University（乌普萨拉大学）；SICS Computer Systems Laboratory, RISE Research Institutes of Sweden AB（瑞典信息通信技术研究所（RISE）计算机系统实验室（SICS））；Department of Information Technology, Division of Systems and Control, Uppsala University（乌普萨拉大学信息技术系系统与控制部）
Search Multilayer Perceptron-Based Fusion for Efficient and Accurate Siamese Tracking
Institute of Mining Artificial Intelligence, Chinese Institute of Coal Science（采矿人工智能研究所，中国煤炭科学研究院）；Department of Computer Science, City University of Hong Kong（计算机科学系，香港城市大学）；Image Processing Center, School of Astronautics, Beihang University（图像处理中心，航天学院，北航）；State Key Laboratory of Intelligent Coal Mining and Strata Control（智能煤炭开采与岩层控制国家重点实验室）
Performance Assessment of different Machine Learning Algorithm for Life-Time Prediction of Solder Joints based on Synthetic Data
Fraunhofer Institute for Ceramic Technologies and Systems IKTS（弗劳恩霍夫陶瓷技术与系统研究所IKTS）；Technische Universität Dresden（德累斯顿工业大学）；Dresden Center for Fatigue and Reliability (DCFR)（德累斯顿疲劳与可靠性中心（DCFR））
Auto Quantum Machine Learning for Multisource Classification
Center of Excellence in Artificial Intelligence, AGH University（人工智能卓越中心，AGH大学）；Nicolaus Copernicus Astronomical Center, Polish Academy of Sciences（尼古拉·哥白尼天文中心，波兰科学院）；Systems Research Institute, Polish Academy of Sciences（系统研究所，波兰科学院）
Automatic Construction of Pattern Classifiers Capable of Continuous Incremental Learning and Unlearning Tasks Based on Compact-Sized Probabilistic Neural Network
Department of Computer Engineering, College of Science & Technology（计算机工程系，科学与技术学院）
