会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 2. 发明申请
    • A MACHINE-LEARNING APPROACH TO MODELING BIOLOGICAL ACTIVITY FOR MOLECULAR DESIGN AND TO MODELING OTHER CHARACTERISTICS
    • 建立分子生物学活动的机器学习方法和模拟其他特征
    • WO1994028504A1
    • 1994-12-08
    • PCT/US1994005877
    • 1994-05-20
    • ARRIS PHARMACEUTICALCHAPMAN, DavidCRITCHLOW, RogerDIETTERICH, TomJAIN, Ajay, N.LATHROP, RickPEREZ, Tomas, Lozano
    • ARRIS PHARMACEUTICAL
    • G06F15/60
    • C07K1/00G06F19/704G06F19/706G06F19/707Y10S706/92
    • Explicit representation of molecular shape of molecules is combined with neural network learning methods to provide models with high predictive ability that generalize to different chemical classes where structurally diverse molecules exhibiting similar surface characteristics are treated as similar. A new machine-learning methodology is disclosed that can accept multiple representations of objects (100) and construct models (102-114) that predict characteristics of those objects (116). An extension of this methodology can be applied in cases where the representations of the objects are determined by a set of adjustable parameters. An iterative process applies intermediate models to generate new representations of the objects by adjusting parameters (108) and repeatedly retrains the models to obtain better predictive models. This method can be applied to molecules because each molecule can have many orientations and conformations, or representations, that are determined by a set of translation, rotation, and torsion angle parameters.
    • 分子分子形状的显式表示与神经网络学习方法相结合,以提供具有高预测能力的模型,将其泛化为不同的化学类别,其中表现出相似表面特征的结构多样的分子被认为是相似的。 公开了一种新的机器学习方法,其可以接受对象(100)的多个表示并且构造预测那些对象(116)的特征的模型(102-114)。 在通过一组可调参数确定对象的表示的情况下,可以应用该方法的扩展。 迭代过程通过调整参数(108)并重复地重新模拟模型以获得更好的预测模型,应用中间模型来生成对象的新表示。 该方法可以应用于分子,因为每个分子可以具有由一组平移,旋转和扭转角参数确定的许多取向和构象或表示。
    • 10. 发明申请
    • HIGH DENSITY INTERCONNECT STRUCTURES CONFIGURED FOR MANUFACTURING AND PERFORMANCE
    • 配置用于制造和性能的高密度互连结构
    • WO2018004619A1
    • 2018-01-04
    • PCT/US2016/040486
    • 2016-06-30
    • BRAUNISCH, HenningAYGUN, KemalJAIN, AjayQIAN, Zhiguo
    • BRAUNISCH, HenningAYGUN, KemalJAIN, AjayQIAN, Zhiguo
    • H01L23/48H01L23/00H01L23/495H01L23/498H01L23/522
    • Discussed generally herein are methods and devices including or providing a high density interconnect structure. A high density interconnect structure can include a stack of alternating dielectric layers and metallization layers comprising at least three metallization layers including conductive material with low k dielectric material between the conductive material, and at least two dielectric layers including first medium k dielectric material with one or more first vias extending therethrough, the at least two dielectric layers situated between two metallization layers of the at least three metallization layers, a second medium k dielectric material directly on a top surface of the stack, a second via extending through the second medium k dielectric material, the second via electrically connected to conductive material in a metallization layer of the three or more metallization layers, and a pad over the second medium k dielectric material and electrically connected to the second via.
    • 这里通常讨论的是包括或提供高密度互连结构的方法和设备。 高密度互连结构可以包括交替介电层和金属化层的叠层,所述金属化层包括至少三个金属化层,所述至少三个金属化层包括在导电材料之间具有低k介电材料的导电材料,以及至少两个介电层,包括第一介质k介电材料, 所述至少两个电介质层位于所述至少三个金属化层的两个金属化层之间,第二介质k电介质材料直接位于所述堆叠的顶表面上,第二通孔延伸穿过所述第二介质k电介质 所述第二通孔电连接到所述三个或更多个金属化层的金属化层中的导电材料,所述第二介质k电介质材料上方的焊盘并且电连接到所述第二通孔。