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。

公开(公告)号：US5504838A

公开(公告)日：1996-04-02

申请号：US206855

申请日：1994-03-07

申请人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi

发明人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi

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 outputs an output signal which is indicative of a result of the processing. The neuron unit 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 generating part for generating new weight functions based on an error signal representing an error between the output signal of the forward process part and a teaching signal 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 error signal includes first and second error signal components representing pulse densities.

摘要翻译： 神经元单元处理多个输入信号并输出​​指示处理结果的输出信号。 神经元单元包括用于接收输入信号的输入线，包括用于提供加权函数的供给部分的前向处理部分和使用加权函数之一对每个输入信号执行操作的操作部分，并且用于输出输出 信号和自学习部分，包括用于基于表示正向处理部分的输出信号与示教信号之间的误差的误差信号产生新的加权函数的生成部分和用于改变由所述前向处理部分提供的加权函数的变化部分 将前向处理部分的一部分提供给由生成部分生成的新的加权函数。 误差信号包括表示脉冲密度的第一和第二误差信号分量。

公开(公告)号：US5167006A

公开(公告)日：1992-11-24

申请号：US629632

申请日：1990-12-18

申请人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi

发明人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi

IPC分类号： G06N3/063

CPC分类号： G06N3/063

摘要： A neuron unit processes a plurality of input signals and outputs an output signal which is indicative of a result of the processing. The neuron unit 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 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.

摘要翻译： 神经元单元处理多个输入信号并输出​​指示处理结果的输出信号。 神经元单元包括用于接收输入信号的输入线，包括用于提供加权函数的供给部分的前向处理部分和使用加权函数之一对每个输入信号执行操作的操作部分，并且用于输出输出 信号和自学习部分，其包括基于正向处理部分的输出信号和示教信号之间的误差产生新的加权函数的生成部分和用于改变由前向处理的供给部分提供的加权函数的变化部分 部分由生成部分生成的新的权重函数。

公开(公告)号：US5619617A

公开(公告)日：1997-04-08

申请号：US128707

申请日：1993-09-30

申请人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi

发明人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi

IPC分类号： G06N3/063 ,  G06E1/00 ,  G06E3/00 ,  G06F15/18

CPC分类号： G06N3/063

摘要： A neuron unit processes a plurality of input signals and outputs an output signal which is indicative of a result of the processing. The neuron unit 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 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.

摘要翻译： 神经元单元处理多个输入信号并输出​​指示处理结果的输出信号。 神经元单元包括用于接收输入信号的输入线，包括用于提供加权函数的供给部分的前向处理部分和使用加权函数之一对每个输入信号执行操作的操作部分，并且用于输出输出 信号和自学习部分，其包括基于正向处理部分的输出信号和示教信号之间的误差产生新的加权函数的生成部分和用于改变由前向处理的供给部分提供的加权函数的变化部分 部分由生成部分生成的新的权重函数。

公开(公告)号：US5581662A

公开(公告)日：1996-12-03

申请号：US441418

申请日：1995-05-15

申请人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi

发明人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi

IPC分类号： G06N3/063 ,  G06F15/18

CPC分类号： G06N3/063

摘要： A hierarchical signal processing apparatus includes aggregates having logic operation portions. The apparatus compares a final output signal from a logic operation portion in a final aggregate with a teaching signal, and generates an error signal by taking a signal which exists only in the teaching signal as a positive error signal, and taking a signal which exists only in said final output signal as a negative error signal. An error signal generating portion in the apparatus generates a positive error signal of a logic operating portion within a certain aggregate which supplies one or more output signals thereof to said logic operation means of another aggregate based on one or more logic operations on the excitatory weight function signal of said weight function signal, the positive error signal, the inhibitory weight function signal of said weight function signal and the negative error signal, and also generates a negative error signal of said logic operation means within said certain aggregate which supplies one or more output signals thereof to said logic operation means of said other aggregate based on one or more logic operations on the inhibitory weight function signal of said weight function signal, the positive error signal of said other aggregate, the excitatory weight function signal of said weight function signal and the negative error signal.

摘要翻译： 分级信号处理装置包括具有逻辑运算部分的聚合。 该装置将来自最终聚合中的逻辑运算部分的最终输出信号与示教信号进行比较，并且通过仅将在教学信号中存在的信号作为正误差信号，并且仅采用仅存在的信号来产生误差信号 在所述最终输出信号中作为负误差信号。 该装置中的误差信号产生部分产生一定聚集内的逻辑运算部分的正误差信号，该积分误差信号基于对兴奋性加权函数的一个或多个逻辑运算向另一聚合体的一个或多个输出信号提供一逻辑运算装置 所述加权函数信号的信号，正误差信号，所述加权函数信号的抑制加权函数信号和负误差信号，并且还产生所述逻辑运算装置的负误差信号，所述负误差信号提供一个或多个输出 基于对所述加权函数信号的抑制加权函数信号，所述另一聚合体的正误差信号，所述加权函数信号的兴奋度权重函数信号和所述加权函数信号的抑制加权函数信号的一个或多个逻辑运算， 负误差信号。

公开(公告)号：US5333241A

公开(公告)日：1994-07-26

申请号：US889380

申请日：1992-05-28

申请人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi

发明人： Toshiyuki Furuta ,  Hiroyuki Horiguchi ,  Hirotoshi Eguchi ,  Yutaka Ebi ,  Tatsuya Furukawa ,  Yoshio Watanabe ,  Toshihiro Tsukagoshi

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 outputs an output signal which is indicative of a result of the processing. The neuron unit 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 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.

摘要翻译： 神经元单元处理多个输入信号并输出​​指示处理结果的输出信号。 神经元单元包括用于接收输入信号的输入线，包括用于提供加权函数的供给部分的前向处理部分和使用加权函数之一对每个输入信号执行操作的操作部分，并且用于输出输出 信号和自学习部分，其包括基于正向处理部分的输出信号和示教信号之间的误差产生新的加权函数的生成部分和用于改变由前向处理的供给部分提供的加权函数的变化部分 部分由生成部分生成的新的权重函数。

公开(公告)号：US4504844A

公开(公告)日：1985-03-12

申请号：US433929

申请日：1982-10-12

申请人： Yutaka Ebi ,  Tadashi Fujii ,  Takuro Sekiya ,  Masanori Horike ,  Tatsuya Furukawa ,  Masaaki Tachiki

发明人： Yutaka Ebi ,  Tadashi Fujii ,  Takuro Sekiya ,  Masanori Horike ,  Tatsuya Furukawa ,  Masaaki Tachiki

IPC分类号： B41J2/06 ,  G01D15/16

CPC分类号： B41J2/06 ,  B41J2002/061 ,  B41J2202/22

摘要： An on-demand type ink jet printing apparatus which prints out data in various forms such as characters and numerals by the combination of dots formed by ink droplets on a sheet of paper. An ink ejection head of the printer includes control electrodes disposed in at least one ink passageway. Ink droplets are formed and caused to fly by electric fields developed in the vicinity of the control electrodes when voltages are applied thereacross. Multiport ink ejection is achieved by the provision of a plurality of ink passageways in the head. The voltage supply to the control electrodes is controllable so that ink droplets may be formed and caused into flight in response to print signals.A channel defining each ink passageway can be shaped easily yet with accuracy utilizing an etching characteristic particular to a specific crystal face.A plurality of acceleration electrodes may be employed to promote desirable flight of ink droplets. Further, a counter electrode may be located in the head to face the control electrodes so that the ink droplets will be formed and fly in a further efficient and stable manner.

摘要翻译： 一种点播式喷墨打印设备，其通过由墨滴形成的点组合在一张纸上打印诸如字符和数字的各种形式的数据。 打印机的喷墨头包括设置在至少一个墨通道中的控制电极。 当在其上施加电压时，通过在控制电极附近产生的电场，形成墨滴并使其飞行。 通过在头部中设置多个墨水通道来实现多端口墨水喷射。 对控制电极的电压供应是可控制的，使得可以响应于打印信号而形成墨滴并引起飞行。 限定每个墨水通道的通道可以利用特定于特定晶面的蚀刻特性而精确地成形。 可以使用多个加速电极来促进墨滴的理想飞行。 此外，对置电极可以位于头部中以面对控制电极，使得墨滴将形成并以更有效和稳定的方式飞行。

公开(公告)号：US4677845A

公开(公告)日：1987-07-07

申请号：US804612

申请日：1985-12-05

申请人： Kouji Izumi ,  Masanori Horike ,  Tatsuya Furukawa ,  Hiromichi Komai ,  Osamu Naruse ,  Yutaka Ebi

发明人： Kouji Izumi ,  Masanori Horike ,  Tatsuya Furukawa ,  Hiromichi Komai ,  Osamu Naruse ,  Yutaka Ebi

IPC分类号： B41J2/175 ,  G01N11/04

CPC分类号： G01N11/04 ,  Y10T137/2506

摘要： A device for detecting viscosity of a liquid which varies with time includes a first tank provided with an overflow section for maintaining a predetermined liquid height, and a second tank fluidly communicated to the first tank and provided with a restricted outlet, or orifice. While a liquid is circulated through the two tanks by a pump, a height sensor which is dipped in the liquid in the second tank senses a liquid height in the tank in terms of capacitance. The output of the height sensor is representative of a viscosity of the liquid.

摘要翻译： 用于检测随时间变化的液体粘度的装置包括设置有用于保持预定液体高度的溢流部分的第一罐和与第一罐流体连通并设置有限制出口或孔口的第二罐。 当液体通过泵循环通过两个罐时，浸入第二罐中的液体中的高度传感器以电容方式感测罐中的液体高度。 高度传感器的输出代表液体的粘度。

公开(公告)号：US4535339A

公开(公告)日：1985-08-13

申请号：US525390

申请日：1983-08-22

申请人： Masanori Horike ,  Tatsuya Furukawa ,  Yutaka Ebi ,  Hiroshi Yamazaki

发明人： Masanori Horike ,  Tatsuya Furukawa ,  Yutaka Ebi ,  Hiroshi Yamazaki

IPC分类号： B41J2/115 ,  B41J2/12 ,  G01D15/18

CPC分类号： B41J2/12

摘要： The velocity of flying charged ink drops is detected and the ink pressure is so controlled as to make the ink velocity coincide with a predetermined target velocity. A gutter for catching non-printing ink drops is made of a conductive material, while a charge detector circuit is connected to the gutter to generate a signal indicative of a potential change corresponding to impingement of a charged ink drop on the gutter, thereby detecting the flight of a charged ink drop. The pump pressure is varied in response to a difference between the actual and target velocities so that the ink pressure or velocity is adjusted in arithmetic progression reducing a time period required for the actual velocity to converge to the target.

摘要翻译： 检测飞行的带电墨滴的速度，并且如此控制油墨压力以使油墨速度与预定目标速度一致。 用于捕获非印刷墨滴的沟槽由导电材料制成，而电荷检测器电路连接到沟槽以产生指示对应于沟槽上的带电墨滴的撞击的电位变化的信号，从而检测 飞行一个充电的墨滴。 泵压力响应于实际速度和目标速度之间的差异而变化，使得油墨压力或速度在算术进程中被调节，从而减少实际速度收敛到目标所需的时间段。

公开(公告)号：US4510509A

公开(公告)日：1985-04-09

申请号：US472530

申请日：1983-03-07

申请人： Masanori Horike ,  Tatsuya Furukawa ,  Takuro Sekiya ,  Yutaka Ebi ,  Takuro Isayama ,  Masaaki Tachiki

发明人： Masanori Horike ,  Tatsuya Furukawa ,  Takuro Sekiya ,  Yutaka Ebi ,  Takuro Isayama ,  Masaaki Tachiki

IPC分类号： B41J2/14 ,  B41J2/155 ,  G01D15/18

CPC分类号： B41J2/1433 ,  B41J2/155

摘要： A new nozzle structure is disclosed for an ink ejection head of an electric field on-demand type ink jet printer. A plurality of circular nozzles and first electrodes integral with the nozzles are arranged along the widthwise direction (X direction) and feed direction (Y direction) of a sheet of paper. A plurality of lead terminals are individually connected to the arrays of the first electrodes each of which extends in the Y direction. Second electrodes are located at the rear of the first electrodes and individually connected to the arrays of the first electrode each of which extends in the X direction. A third or counter electrode is positioned in front of the first electrodes and at the back of the sheet. Each of the second electrodes is mounted on a nozzle plate or a nozzle support. The first electrodes are supplied with voltage pulses corresponding to image data, the second electrodes for printing with a voltage opposite in polarity to the voltage pulses, and the second electrodes for non-printing with a zero voltage or a voltage common in polarity to the voltage pulses sequentially and repeatedly on the time sharing basis. The third electrode is applied with a constant voltage of the opposite polarity to the voltage pulses.

摘要翻译： 公开了一种用于电场点播式喷墨打印机的喷墨头的新喷嘴结构。 沿着纸张的宽度方向（X方向）和供给方向（Y方向）排列多个与喷嘴一体的圆形喷嘴和第一电极。 多个引线端子分别连接到每个沿Y方向延伸的第一电极的阵列。 第二电极位于第一电极的后部，并且分别连接到第一电极的阵列，每个阵列沿X方向延伸。 第三或对电极位于第一电极的前面和片的背面。 每个第二电极安装在喷嘴板或喷嘴支架上。 向第一电极提供与图像数据相对应的电压脉冲，用于以与电压脉冲极性相反的电压进行打印的第二电极，以及用于零电压或与电压极性相同的电压的非打印的第二电极 在时间分配的基础上顺序地和反复地进行脉冲。 施加与电压脉冲相反极性的恒定电压的第三电极。