Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of Chinese Academy of Sciences(中国科学院大学);University of Central Florida(中佛罗里达大学);Portland State University(波特兰州立大学);Institute for Infocomm Research(资讯通信研究院);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Meng Xiao, Dongjie Wang, Min Wu, Kunpeng Liu, Hui Xiong, Yuanchun Zhou, Yanjie Fu
备注:
Under review of TKDE. arXiv admin note: substantial text overlap with arXiv:2205.14526
Feature transformation aims to extract a good representation (feature) space by mathematically transforming existing features. It is crucial to address the curse of dimensionality, enhance model generalization, overcome data sparsity, and expand the availability of classic models. Current research focuses on domain knowledge-based feature engineering or learning latent representations; nevertheless, these methods are not entirely automated and cannot produce a traceable and optimal representation space. When rebuilding a feature space for a machine learning task, can these limitations be addressed concurrently? In this extension study, we present a self-optimizing framework for feature transformation. To achieve a better performance, we improved the preliminary work by (1) obtaining an advanced state representation for enabling reinforced agents to comprehend the current feature set better; and (2) resolving Q-value overestimation in reinforced agents for learning unbiased and effective policies. Finally, to make experiments more convincing than the preliminary work, we conclude by adding the outlier detection task with five datasets, evaluating various state representation approaches, and comparing different training strategies. Extensive experiments and case studies show that our work is more effective and superior.
Traceable Group-Wise Self-Optimizing Feature Transformation Learning: A Dual Optimization Perspective
Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of Chinese Academy of Sciences(中国科学院大学);University of Central Florida(中佛罗里达大学);Institute for Infocomm Research, Agency for Science(新加坡科技研究局资讯通信研究院);Portland State University(波特兰州立大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Guangzhou HKUST Fok Ying Tung Research Institute(广州香港科技大学霍英东研究院)
Fast Fourier Transformation for Optimizing Convolutional Neural Networks in Object Recognition
Texas Tech University(得克萨斯理工大学);Georgia Institute of Technology(佐治亚理工学院);State University of New York at Buffalo(纽约州立大学布法罗分校)
本文提出了使用基于快速傅立叶变换的U-网(一种改进的全卷积网络),并在神经网络中执行图像卷积。利用快速傅立叶变换,它降低了卷积神经网络(CNN)中涉及的图像卷积成本,从而降低了整体计算成本。该模型从图像中识别出目标信息。我们应用快速傅立叶变换算法的图像数据集,以获得更多的图像数据的信息,然后通过U-Net架构分割它们。更具体地说,我们实现了基于FFT的卷积神经网络,以提高网络的训练时间。所提出的方法被应用到公开可用的宽生物图像基准收集(BBBC)数据集。我们的模型证明了卷积过程中的训练时间从$600-700$ ms/步提高到$400-500$ ms/步。我们使用Intersection over Union(IoU)度量评估了我们模型的准确性,显示出显着的改进。
Dynamic Controlled Variables Based Dynamic Self-Optimizing Control
College of Chemical and Biological Engineering, Zhejiang University, Hangzhou, Zhejiang Province, P.R. China(浙江大学化学与生物工程学院);Institute of Zhejiang University-Quzhou, Quzhou, Zhejiang Province, P.R. China(浙江大学Quzhou研究院)
SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation
Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore(眼科学系,Yong Loo Lin医学院,新加坡国立大学,新加坡);Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, India(计算与数据科学系,印度科学研究院,班加罗尔,卡纳塔克邦,印度)
The Multiplex Classification Framework: optimizing multi-label classifiers through problem transformation, ontology engineering, and model ensembling
Universidad Nacional del Sur(国立南方大学);National Scientific and Technological Research Council of Argentina (CONICET)(阿根廷国家科学技术研究委员会(CONICET));Centro Nacional Patagónico (CENPAT-CONICET)(巴塔哥尼亚国家中心(CENPAT-CONICET))
Optimizing Likelihood-free Inference using Self-supervised Neural Symmetry Embeddings
Massachusetts Institute of Technology(麻省理工学院);Institute for Artificial Intelligence and Fundamental Interactions (IAIFI)(人工智能与基础相互作用研究所(IAIFI));University of Pennsylvania(宾夕法尼亚大学);University of Minnesota(明尼苏达大学)