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
    • 9. 发明授权
    • Video signal reproducing apparatus with memory
    • 具有存储器的视频信号再现装置
    • US4882633A
    • 1989-11-21
    • US139780
    • 1987-12-30
    • Yoshihiro NakataniTsutomu Fukatsu
    • Yoshihiro NakataniTsutomu Fukatsu
    • H04N9/877
    • H04N9/877
    • A video signal reproducing apparatus for reproducing a video signal recorded in many tracks which are formed on a record bearing medium has a high-speed video signal reproducing mode and is characterized by the inclusion of: A memory arranged to temporarily store the video signal read out from the medium by the reproducing head; a step-up circuit arranged to generate a step-up signal which is obtained by stepping up a periodic signal relative to the medium tracing period of the reproducing head; and a control circuit which is arranged to control signal writing into the memory in accordance with the step-up signal produced from the step-up circuit.
    • 用于再现记录在记录承载介质上的许多轨道中的视频信号的视频信号再现装置具有高速视频信号再现模式,其特征在于包括:存储器,其被布置为临时存储读出的视频信号 从媒体由再现头; 升压电路,被配置为产生升压信号,该升压信号通过相对于再现头的介质追踪周期升高周期信号而获得; 以及控制电路,其被配置为根据从升压电路产生的升压信号来控制到存储器中的信号写入。
    • 10. 发明授权
    • Learning system operated through a layered neural network
    • 学习系统通过分层神经网络运行
    • US5563983A
    • 1996-10-08
    • US436602
    • 1995-05-08
    • Chikanori NozakiJunko MuraiYoshihiro Nakatani
    • Chikanori NozakiJunko MuraiYoshihiro Nakatani
    • G06F15/18G06G7/60G06N3/04G06N3/08G06N99/00
    • G06N3/049Y10S706/926
    • The present invention predicts an output result in response to unknown input data using a layered neural network. For example, learning data collected in time series with rate of changes included are learned through the layered neural network. As a result, a predicted value can be obtained with a smaller amount of learning data within a shorter learning time. The present invention comprises a rate of change calculating unit for calculating the rate of change of time-series data at two different time points, and a network generating unit for controlling the learning steps performed by the layered neural network using at least the rate of change of data as learning data so as to establish a neural network in which a weight value is determined for learning data. As a predicting system, it further comprises at least a neural network recognizing unit for applying to the neural network established by the network generating unit an output of the rate of change calculating unit outputted in response to input predicting data, and for obtaining a prediction result.
    • 本发明使用分层神经网络来预测响应未知输入数据的输出结果。 例如,通过分层神经网络学习以时间序列收集的学习数据,包括变化率。 结果,可以在更短的学习时间内用较少量的学习数据来获得预测值。 本发明包括用于计算两个不同时间点上的时间序列数据的变化率的变化率计算单元,以及用于使用至少变化率来控制由分层神经网络执行的学习步骤的网络生成单元 的数据作为学习数据,以便建立其中为学习数据确定权重值的神经网络。 作为预测系统,还包括至少一个神经网络识别单元,用于向由网络生成单元建立的神经网络应用响应于输入预测数据输出的变化率计算单元的输出,并且用于获得预测结果 。