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
    • 13. 发明申请
    • Biomimic artificial neuron
    • 生物仿真人造神经元
    • US20050102247A1
    • 2005-05-12
    • US10893407
    • 2004-07-16
    • Richard WellsBruce Barnes
    • Richard WellsBruce Barnes
    • G06E1/00G06E3/00G06F15/18G06G7/00G06N20060101G06N3/06G06N3/063
    • G06N3/063
    • An artificial neuron is formed from an input subcircuit, a capacitor free leaky integrator subcircuit, and an output switching subcircuit. The input subcircuit is configured to supply a pulsed input signal. The capacitor free leaky integrator subcircuit is configured to supply a parasitic capacitance and to utilize the parasitic capacitance to provide differing time constants for the rising and falling edges of an output signal produced in response to the pulsed input signal. The output switching subcircuit s configured to, upon receipt of a sufficient output signal from the capacitor free leaky integrator subcircuit, switch off the input subcircuit and to release a neuron firing signal.
    • 人造神经元由输入分支电路,无电容泄漏积分器子电路和输出开关分支电路形成。 输入子电路配置为提供脉冲输入信号。 电容器无泄漏积分器子电路配置为提供寄生电容并利用寄生电容为响应脉冲输入信号产生的输出信号的上升沿和下降沿提供不同的时间常数。 输出开关子电路被配置为在从电容器无泄漏积分器子电路接收到足够的输出信号时,关闭输入子电路并释放神经元触发信号。
    • 17. 发明申请
    • AUTOMATED CARD COUNTER AND METHOD OF AUTOMATICALLY COUNTING CARDS
    • 自动卡计数器和自动计数卡的方法
    • WO2004081861A3
    • 2005-09-01
    • PCT/US2004007424
    • 2004-03-11
    • DYNETICS ENGINEERING CORP INCGRABER WARREN SKUESTER RYAN J
    • GRABER WARREN SKUESTER RYAN J
    • G06M1/10G06M9/00G06N20060101H01J40/14
    • G06M9/00G06M1/101
    • An automated card counter (20) with a housing (22) with an open front with a card deck assembly (24) having a front opening to a card counting location and an underlying support for a stack (29) of cards (30) such as credits cards, with an optical sensing system for detecting the edges of the cards (30) in the stack (29) to determine the number, or count, of cards (30) in the stack (29) includes a light source (64) composed of high intensity light emitting diodes directing red light rearward and downwardly away from the front card deck opening and along the entire length of the stack of cards through a window (96), a mirror (76) for simultaneous reflecting a complete image of the entire stack of cards downwardly and rearward to another mirror (100) that reflects the complete image rearward and horizontally to a lens system (108) with a relatively wide depth of field to focus the image on a photosensor (110) composed of charge coupled devices that convert signals to numbers by an A/D converter and processed by a microprocessor (116) to distinguish real cards from other objects
    • 一种自动卡片计数器(20),其具有带开口前部的壳体(22),卡片卡板组件(24)具有卡片计数位置的前开口和用于卡片(30)的堆叠(29)的底部支撑件, 作为信用卡,具有用于检测堆叠(29)中的卡(30)的边缘的光学感测系统以确定堆叠(29)中的卡(30)的数量或数量包括光源(64) ),其由高强度发光二极管组成,所述高强度发光二极管通过窗口(96)将红灯向后和向后远离所述前卡片卡口开口并沿着所述卡堆叠的整个长度;反射镜(76),用于同时反映 整个卡堆向下和向后到另一个反射镜(100),其将完整图像向后和水平地反射到具有相对较高景深的透镜系统(108),以将图像聚焦在由电荷耦合的光电传感器(110) 通过A / D公司将信号转换为数字的设备 并由微处理器(116)处理,以将真实卡与其他物体区分开
    • 19. 发明公开
    • SYSTEM UND VERFAHREN ZUR RECHNERBASIERTEN ANALYSE GROSSER DATENMENGEN
    • 系统和方法基于计算机的分析数据集BIG
    • EP2396752A2
    • 2011-12-21
    • EP09827247.9
    • 2009-11-19
    • Optimining GmbH
    • DORNEICH, Ansgar
    • G06N20060101
    • G06N3/10G06K9/6251G06K9/6298
    • For a computer system used for data analysis, the training time is to be significantly reduced through technical means; also, the storage space required is to be noticeably reduced through the use of technical measures. To this end, an electronic data processing system for analyzing data is proposed, comprising at least one analysis computer, wherein the analysis computer is adapted and programmed to implement a self-adapting neural network that is subjected to training by a plurality of data sets with many features, wherein the neurons of the neural net are assigned initial neuron weights, the neurons of the neural net are assigned neuron weights that are extracted from said plurality of data sets with said many features, a training involves a plurality of training phases, and wherein each training phase comprises a certain number of training cycles, wherein at the beginning of each training phase, either neurons whose neuron weights are made up of weights of existing neurons, at least partially, are added into the neural network, or neurons are removed from the neural net and the neuron weights of the remaining neurons are weighted with portions of the weights of the removed neurons, at least partially.