利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

7 条记录 (耗时 0.041 秒)

    Liquid jet recording head having improved radiator member
    3.
    发明授权
    Liquid jet recording head having improved radiator member 失效
    具有改进的散热器构件的液体喷射记录头

    公开(公告)号：US5600356A

    公开(公告)日：1997-02-04

    申请号：US365069

    申请日：1994-12-28

    申请人： Takuro Sekiya ,  Takashi Kimura ,  Masanori Horike ,  Shuji Motomura ,  Masami Kadonaga

    发明人： Takuro Sekiya ,  Takashi Kimura ,  Masanori Horike ,  Shuji Motomura ,  Masami Kadonaga

    IPC分类号： B41J2/14 ,  B41J2/05

    CPC分类号： B41J2/14129 ,  B41J2/14072

    摘要： A liquid jet recording head includes a liquid path member having a plurality of liquid flow paths, each of the liquid flow paths being filled with a recording liquid, an orifice being formed at an end of each of the liquid flow paths, and a heater base member having a plurality of heater members and a plurality of radiator members. The heater base member is connected to the liquid path member, each of the heater members having a heater portion, the heater portion generating heat in accordance with a power supplied to it. Each of the radiator members is thermally coupled to the heater portion of one of the heater members so that the amount of heat transmitted from the heater portion to the recording liquid on the heater portion changes in a predetermined direction. When a power is supplied to the heater portion, a bubble is generated in the recording liquid and located at an area on the heater portion, the area having a size corresponding to the power supplied to the heater portion, the bubble causing a recording liquid droplet to be jetted from the orifice.

    摘要翻译： 液体喷射记录头包括具有多个液体流动路径的液体通道部件，每个液体流动路径填充有记录液体，在每个液体流动路径的端部形成有孔口，加热器基座 构件具有多个加热器构件和多个散热器构件。 加热器基部件连接到液体通道部件，每个加热器部件具有加热器部分，加热器部分根据供应给其的电力产生热量。 每个散热器构件热耦合到一个加热器构件的加热器部分，使得从加热器部分传递到加热器部分上的记录液体的热量在预定方向上变化。 当向加热器部分供电时，在记录液体中产生气泡并且位于加热器部分的区域上，该区域具有与供给加热器部分的功率相对应的尺寸，该气泡引起记录液滴 从孔口喷出。

    Neuron unit
    4.
    发明授权
    Neuron unit 失效
    神经元单位

    公开(公告)号：US5327522A

    公开(公告)日：1994-07-05

    申请号：US989781

    申请日：1992-12-11

    申请人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi ,  Takahiro Watanabe ,  Shuji Motomura ,  Atsuo Hashimoto ,  Sugitaka Oteki ,  Satoshi Otsuki ,  Eiki Aono ,  Takashi Kitaguchi

    发明人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi ,  Takahiro Watanabe ,  Shuji Motomura ,  Atsuo Hashimoto ,  Sugitaka Oteki ,  Satoshi Otsuki ,  Eiki Aono ,  Takashi Kitaguchi

    IPC分类号： G06N3/063 ,  G06F15/18

    CPC分类号： G06N3/063

    摘要： A neuron unit processes a plurality of input signals and for outputs an output signal which is indicative of a result of the processing, and includes input lines for receiving the input signals, a forward process part including a supplying part for supplying weight functions and an operation part for carrying out an operation on each of the input signals using one of the weight functions and for outputting the output signal, and a self-learning part including a function generating part for generating new weight functions based on errors between the output signal of the forward process part and teaching signals and a varying part for varying the weight functions supplied by the supplying part of the forward process part to the new weight functions generated by the generating part. The supplying part includes a memory for storing each weight function in the form of a binary value, and a generating circuit for generating a random pulse train based on each binary value stored in the memory. The random pulse train describes each weight function in the form of a pulse signal having a pulse density.

    摘要翻译： 神经元单元处理多个输入信号并输出​​表示处理结果的输出信号，并且包括用于接收输入信号的输入线，前向处理部分，包括用于提供加权函数的提供部分和操作 使用所述加权函数之一对所述输入信号执行操作并输出所述输出信号的部分，以及包括功能生成部分的自学习部分，用于基于所述输入信号的输出信号之间的误差生成新的加权函数 前向处理部分和教学信号，以及变化部分，用于将由前向处理部分的供给部分提供的权重函数改变为由生成部分生成的新的权重函数。 供给部分包括用于以二进制值的形式存储每个加权函数的存储器，以及用于基于存储在存储器中的每个二进制值产生随机脉冲串的产生电路。 随机脉冲串以具有脉冲密度的脉冲信号的形式描述每个权重函数。

    Signal processing apparatus
    5.
    发明授权
    Signal processing apparatus 失效
    信号处理装置

    公开(公告)号：US5588090A

    公开(公告)日：1996-12-24

    申请号：US246342

    申请日：1994-05-19

    申请人： Toshiyuki Furuta ,  Shuji Motomura ,  Takahiro Watanabe ,  David G. Stork

    发明人： Toshiyuki Furuta ,  Shuji Motomura ,  Takahiro Watanabe ,  David G. Stork

    IPC分类号： G06G7/60 ,  G06F15/18 ,  G06N3/04 ,  G06N3/06 ,  G06N3/063 ,  G11C11/54

    CPC分类号： G06N3/049 ,  G06N3/063

    摘要： A signal processing apparatus has a circuit network which is formed by connecting a plurality of neuron units into a network, each of the neuron being provided with a self-learning means having a weight function varying means and a weight function generating means for generating a variable weight function of the weight function varying means, on the basis of a positive or negative error signal obtained as a result of the comparison between an output signal and a teaching signal. In order to obtain a positive error signal .delta..sub.j(+) and a negative error signal .delta..sub.j(-), there is provided a differential coefficient calculating means for calculating two kinds of differential coefficients for a neuron response function, the calculation being done on the basis of the output signal from the neuron unit.

    摘要翻译： 信号处理装置具有通过将多个神经元单元连接到网络而形成的电路网络，每个神经元都具有自学习装置，该自学习装置具有加权函数改变装置和权重函数产生装置，用于产生变量 基于作为输出信号和示教信号之间的比较的结果获得的正或负误差信号，加权函数改变装置的权重函数。 为了获得正的误差信号Δj（+）和负的误差信号Δj（ - ），提供了一种用于计算神经元响应函数的两​​种微分系数的微分系数计算装置， 来自神经元单位的输出信号的基础。

    Neuron unit and neuron unit network
    6.
    发明授权
    Neuron unit and neuron unit network 失效
    神经元单位和神经元单位网络

    公开(公告)号：US5324991A

    公开(公告)日：1994-06-28

    申请号：US989605

    申请日：1992-12-11

    申请人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Atsuo Hashimoto ,  Sugitaka Oteki ,  Toshihiro Tsukagoshi ,  Satoshi Otsuki ,  Eiki Aono ,  Shuji Motomura ,  Takahiro Watanabe

    发明人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Atsuo Hashimoto ,  Sugitaka Oteki ,  Toshihiro Tsukagoshi ,  Satoshi Otsuki ,  Eiki Aono ,  Shuji Motomura ,  Takahiro Watanabe

    IPC分类号： G06N3/063 ,  G06F15/18

    CPC分类号： G06N3/063

    摘要： A neuron unit processes a plurality of binary input signals and outputs a neuron output signal which is indicative of a result of the processing. The neuron unit is provided with a plurality of first gates respectively for carrying out a logical operation on a binary input signal and a weighting coefficient, a second gate for carrying out a logical operation on an excitatory output signal of each of the first gates, a third gate for carrying out a logic operation on an inhibitory output signal of each of the first gates, a fourth gate for synthesizing output signals of the second and third gates and outputting the neuron output signal, and a generating circuit for generating the weighting coefficients which are supplied to each of the first gates. The generating circuit for generating one weighting coefficient includes a random number generator for generating random numbers, and a comparator for comparing each random number r with a predetermined value q and for outputting a pulse signal having first and second values depending on whether each random number r is such that r.ltoreq.q or r>q, and each weighting coefficient is described by a pulse density.

    摘要翻译： 神经元单元处理多个二进制输入信号并输出​​指示处理结果的神经元输出信号。 神经元单元分别设置有多个第一门，用于对二进制输入信号和加权系数进行逻辑运算，第二门用于对每个第一门的兴奋性输出信号进行逻辑运算， 第三门，用于对每个第一门的抑制输出信号进行逻辑运算，第四门，用于合成第二和第三门的输出信号并输出​​神经元输出信号;以及产生电路，用于产生加权系数， 被提供给每个第一门。 用于产生一个加权系数的产生电路包括用于产生随机数的随机数发生器和用于将每个随机数r与预定值q进行比较的比较器，并且用于根据每个随机数r是否输出具有第一和第二值的脉冲信号 是这样的，r = q或r> q，并且每​​个加权系数由脉冲密度来描述。

    Neural network and method for training the neural network
    7.
    发明授权
    Neural network and method for training the neural network 失效
    神经网络和训练神经网络的方法

    公开(公告)号：US5283855A

    公开(公告)日：1994-02-01

    申请号：US795952

    申请日：1991-11-21

    申请人： Shuji Motomura ,  Toshiyuki Furuta ,  Hirotoshi Eguchi

    发明人： Shuji Motomura ,  Toshiyuki Furuta ,  Hirotoshi Eguchi

    IPC分类号： G06F15/18 ,  G06G7/60 ,  G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06N99/00

    CPC分类号： G06N3/08 ,  G06N3/04 ,  G06N3/0635

    摘要： A method and apparatus are disclosed that modify [ies] and generalize [s] the use in artificial neural networks of the error backpropagation algorithm. Each neuron unit first divides a plurality of weighted inputs into more than one group, then sums up weighted inputs in each group to provide each group's intermediate outputs, and finally processes the intermediate outputs to produce an output of the neuron unit. Since the method uses, when modifying each weight, a partial differential coefficient generated by partially-differentiating the output of the neuron unit by each weighted input, the weight can be properly modified even if the output of a neuron unit as a function of intermediate outputs has a plurality of variables corresponding to the number of groups. Since the conventional method uses only one differential coefficient, that is, the differential coefficient of the output of a neuron unit differentiated by the sum of all weighted inputs in a neuron unit, for all weights in a neuron unit, it may be said that the method according to the present invention generalizes the conventional method. The present invention is especially useful for pulse density neural networks which express data as an ON-bit density of a bit string.

    摘要翻译： 公开了一种改进误差反向传播算法在人工神经网络中的使用和概括的方法和装置。 每个神经元单元首先将多个加权输入划分成多于一个组，然后对每组中的加权输入求和，以提供每组的中间输出，并最终处理中间输出以产生神经元单元的输出。 由于该方法使用修改每个权重时，通过由每个加权输入部分地区分神经元单元的输出而产生的偏微分系数，所以即使作为中间输出的函数的神经元单元的输出，也可以适当地修改权重 具有与组数相对应的多个变量。 由于常规方法仅使用一个微分系数，即，对于神经元单元中的所有加权输入，由神经元单位中的所有加权输入之和区分的神经元单位的输出的微分系数，对于神经元单元中的所有权重，可以说是 根据本发明的方法概括了常规方法。 本发明对于将数据表示为位串的ON位密度的脉冲密度神经网络特别有用。