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
    • 55. 发明授权
    • Neural network with learning function based on simulated annealing and
Monte-Carlo method
    • 基于模拟退火和蒙特卡罗方法的具有学习功能的神经网络
    • US5459817A
    • 1995-10-17
    • US38100
    • 1993-03-30
    • Takeshi Shima
    • Takeshi Shima
    • G06F15/18G06G7/60G06N3/04G06N3/063G06N3/08G06N99/00G06F1/00
    • G06N3/063G06N3/08
    • A neural network with a learning function which does not require the backward propagation of the signals for the learning, which is applicable for a case involving the feedback of the synapses or the loop formed by the synapses, and which enables the construction of a large scale neural network by using compact and inexpensive circuit elements. An evaluation value is calculated according to a difference between each output signal of the network and a corresponding teacher signal; a manner of updating the synapse weight factor of each synapse is determined according to an evaluation value change between a present value and a previous value of evaluation value on a basis of the simulated annealing; a randomly changing update control signal is generated according to a random number; and a synapse weight factor of each synapse is updated according to the generated update control signal and the determined manner of updating on a basis of the Monte-Carlo method.
    • 具有学习功能的神经网络,其不需要用于学习的信号的反向传播,其适用于涉及突触或由突触形成的回路的反馈的情况,并且能够构建大规模 神经网络通过使用紧凑和廉价的电路元件。 根据网络的每个输出信号与对应的教师信号之间的差异来计算评估值; 基于模拟退火,根据评价值与评估值的先前值之间的评价值变化来确定更新每个突触的突触重量因子的方式; 根据随机数产生随机变化的更新控制信号; 并且根据生成的更新控制信号和确定的基于蒙特卡罗方法的更新方式来更新每个突触的突触加权因子。
    • 56. 发明授权
    • Neural network device
    • 神经网络设备
    • US5319738A
    • 1994-06-07
    • US734780
    • 1991-07-23
    • Takeshi ShimaYukio Kamatani
    • Takeshi ShimaYukio Kamatani
    • G05B13/02G05B13/00H03K19/20
    • G05B13/027
    • This invention has an object to provide a practical neural network device. The first neural network device of this invention comprises an input circuit for performing predetermined processing of external input information and generating an input signal, an arithmetic processing circuit for performing an arithmetic operation of the input signal in accordance with a plurality of control parameters and generating an output signal, and a control circuit for controlling the control parameters of the arithmetic processing circuit so that the output signal is set to satisfy a predetermined relationship with the input signal, the control circuit including a first cumulative adder for performing cumulative summation of updating amounts of the control parameters for a plurality of proposition patterns supplied as the input signal during learning, and a second cumulative adder for adding currently used control parameter values to values obtained by the first cumulative adder to obtain new control parameter values.
    • 本发明的目的是提供一种实用的神经网络装置。 本发明的第一神经网络装置包括用于执行外部输入信息的预定处理并产生输入信号的输入电路,用于根据多个控制参数执行输入信号的算术运算的运算处理电路, 输出信号,以及控制电路,用于控制运算处理电路的控制参数,使得输出信号被设置为与输入信号满足预定的关系,该控制电路包括第一累积加法器,用于执行累积加法器的更新量 用于在学习期间作为输入信号提供的多个命题模式的控制参数;以及第二累积加法器,用于将当前使用的控制参数值添加到由第一累积加法器获得的值以获得新的控制参数值。
    • 57. 发明申请
    • Onboard Environment Recognition System
    • 车载环境识别系统
    • US20130027511A1
    • 2013-01-31
    • US13559110
    • 2012-07-26
    • Masayuki TAKEMURAShoji MuramatsuTakeshi ShimaMasao Sakata
    • Masayuki TAKEMURAShoji MuramatsuTakeshi ShimaMasao Sakata
    • H04N7/18H04N13/00
    • G06K9/00798G06K9/00805
    • To provide an onboard environment recognition system capable of preventing, with a reduced processing load, erroneous recognition caused by light from a headlight of a vehicle in the surroundings. An onboard environment recognition system 100 has a light source extraction unit 300 that extracts a light source from an image, a light information unit 400 that extracts light whose light source causes erroneous detection in environment recognition based on the position of the light source in the image and estimates light information including information on the light intensity, the three-dimensional position and the light distribution pattern of the light, a road surface reflection estimation unit 500 that estimates, based on the light information, a road surface reflection estimation image region in the image in which the light is reflected on a road surface, and an onboard environment recognition unit 600 that recognizes the environment surrounding the vehicle based on the road surface reflection estimation image region.
    • 为了提供一种车载环境识别系统,其能够以减小的处理负荷来防止由周围环境中的车辆的前灯引起的光的错误识别。 车载环境识别系统100具有从图像中提取光源的光源提取单元300,基于图像中的光源的位置提取光源导致环境识别中的错误检测的光的光信息单元400 并且估计包括关于光的光强度,三维位置和光分布图案的信息的光信息,路面反射估计单元500,其基于光信息估计在所述光信号中的路面反射估计图像区域 光在路面上反射的图像,以及基于路面反射估计图像区域识别车辆周围环境的车载环境识别单元600。
    • 58. 发明申请
    • Vehicle Controller
    • 车载控制器
    • US20120215377A1
    • 2012-08-23
    • US13395327
    • 2010-08-06
    • Masayuki TakemuraShoji MuramatsuIsao FurusawaShinya OhtsujiTakeshi Shima
    • Masayuki TakemuraShoji MuramatsuIsao FurusawaShinya OhtsujiTakeshi Shima
    • G06F17/00
    • B60W30/12B60W2550/143G08G1/167
    • A vehicle controller is provided capable of expanding an application range of departure prevention control while suppressing erroneous control. The vehicle controller includes: a vehicle-mounted camera 600 that captures an image in front of a vehicle; and an ECU 610 that decides one vehicle control method from a plurality of vehicle control methods and controls an actuator with the decided vehicle control method. The vehicle-mounted camera includes an area-specific confidence calculation section 400 that divides the image captured into a plurality of areas on a basis of an acquired image by the capturing and a recognized lane, calculates confidence for each divided area and outputs area-specific confidence information, and the ECU decides a vehicle control method in accordance with the area-specific confidence information.
    • 提供了能够在抑制错误控制的同时扩大防止偏离控制的应用范围的车辆控制器。 车辆控制器包括:车载摄像机600,其捕获车辆前方的图像; 以及ECU 610,其根据多个车辆控制方法判定一个车辆控制方法,并且通过决定的车辆控制方法控制致动器。 车载摄像机包括区域特定置信度计算部分400,其通过捕获和识别的车道将基于获取的图像捕获的图像划分为多个区域,计算每个划分的区域的置信度并输出区域特定 置信信息,ECU根据区域特定置信度判定车辆控制方法。