We study the space of functions computed by random-layered machines, including deep neural networks and Boolean circuits. Investigating the distribution of Boolean functions computed on the recurrent and layer-dependent architectures, we find that it is the same in both models. Depending on the initial conditions and computing elements used, we characterize the space of functions computed at the large depth limit and show that the macroscopic entropy of Boolean functions is either monotonically increasing or decreasing with the growing depth.
Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning
Massachusetts Institute of Technology(麻省理工学院);Singapore-MIT Alliance for Research and Technology (SMART) Centre(新加坡-麻省理工研究与技术联盟(SMART)中心);Omnisens SA(奥姆尼森斯公司)
Impressive computational acceleration by using machine learning for 2-dimensional super-lubricant materials discovery
University of Technology Sydney(悉尼科技大学);University of North Carolina(北卡罗来纳大学);Commonwealth Scientific and Industrial Research Organization(澳大利亚联邦科学与工业研究组织);Monash University(莫纳什大学);La Trobe University(拉筹伯大学);The University of Nottingham(诺丁汉大学);The University of Queensland(昆士兰大学);Flinders University(弗林德斯大学)
Machine Beats Machine: Machine Learning Models to Defend Against Adversarial Attacks
Jožef Stefan International Postgraduate School(约瑟夫·斯特凡国际研究生院);Ubitech Ltd(Ubitech有限公司);University of West Attica(西阿提卡大学);Philips Consumer Lifestyle BV(飞利浦消费生活方式公司);Qlector d.o.o.(Qlector有限责任公司);Jožef Stefan Institute(约瑟夫·斯特凡研究所)
COVID-CT-MD: COVID-19 Computed Tomography (CT) Scan Dataset Applicable in Machine Learning and Deep Learning
Concordia University(康考迪亚大学);McGill University Health Center-Research Institute(麦吉尔大学健康中心研究所);Sunnybrook Health Sciences Centre(桑尼布鲁克健康科学中心);University of Toronto(多伦多大学);University of Montreal(蒙特利尔大学);Iran University of Medical Science(伊朗医科大学)
Can Deep Learning Assist Automatic Identification of Layered Pigments From XRF Data?
Northwestern University(西北大学);Shanghai University(上海大学);The National Archives(英国国家档案馆);The Metropolitan Museum of Art(大都会艺术博物馆);Harvard Art Museums(哈佛艺术博物馆);Art Institute of Chicago(芝加哥艺术博物馆);Delft University of Technology(代尔夫特理工大学)
Generalizability issues with deep learning models in medicine and their potential solutions: illustrated with Cone-Beam Computed Tomography (CBCT) to Computed Tomography (CT) image conversion
University of Texas Southwestern Medical Center(德克萨斯大学西南医学中心)