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
    • 7. 发明申请
    • COMMUNICATION AND SYNAPSE TRAINING METHOD AND HARDWARE FOR BIOLOGICALLY INSPIRED NETWORKS
    • 通信和仿真培训方法和生物信息网络的硬件
    • US20120011088A1
    • 2012-01-12
    • US12831540
    • 2010-07-07
    • Vladimir AparinYi Tang
    • Vladimir AparinYi Tang
    • G06N3/063G06N3/08
    • G06N3/0635G06N3/02G06N3/06G06N3/08G06N99/005
    • Certain embodiments of the present disclosure support techniques for training of synapses in biologically inspired networks. Only one device based on a memristor can be used as a synaptic connection between a pair of neurons. The training of synaptic weights can be achieved with a low current consumption. A proposed synapse training circuit may be shared by a plurality of incoming/outgoing connections, while only one digitally implemented pulse-width modulation (PWM) generator can be utilized per neuron circuit for generating synapse-training pulses. Only up to three phases of a slow clock can be used for both the neuron-to-neuron communications and synapse training. Some special control signals can be also generated for setting up synapse training events. By means of these signals, the synapse training circuit can be in a high-impedance state outside the training events, thus the synaptic resistance (i.e., the synaptic weight) is not affected outside the training process.
    • 本公开的某些实施例支持在生物启发网络中训练突触的技术。 只有一个基于忆阻器的设备可以用作一对神经元之间的突触连接。 突触体重的训练可以用低电流消耗来实现。 所提出的突触训练电路可以由多个输入/输出连接共享,而每个神经元电路只能使用一个数字实现的脉宽调制(PWM)发生器来产生突触训练脉冲。 只有三个阶段的慢时钟可以用于神经元到神经元通信和突触训练。 还可以生成一些特殊的控制信号来设置突触训练事件。 通过这些信号,突触训练电路可以在训练事件之外处于高阻抗状态,因此在训练过程之外不会影响突触电阻(即突触重量)。
    • 8. 发明授权
    • Communication and synapse training method and hardware for biologically inspired networks
    • 生物灵感网络的通信和突触训练方法和硬件
    • US09092736B2
    • 2015-07-28
    • US12831540
    • 2010-07-07
    • Vladimir AparinYi Tang
    • Vladimir AparinYi Tang
    • G06N3/08G06N3/063G06N99/00G06N3/02G06N3/06
    • G06N3/0635G06N3/02G06N3/06G06N3/08G06N99/005
    • Certain embodiments of the present disclosure support techniques for training of synapses in biologically inspired networks. Only one device based on a memristor can be used as a synaptic connection between a pair of neurons. The training of synaptic weights can be achieved with a low current consumption. A proposed synapse training circuit may be shared by a plurality of incoming/outgoing connections, while only one digitally implemented pulse-width modulation (PWM) generator can be utilized per neuron circuit for generating synapse-training pulses. Only up to three phases of a slow clock can be used for both the neuron-to-neuron communications and synapse training. Some special control signals can be also generated for setting up synapse training events. By means of these signals, the synapse training circuit can be in a high-impedance state outside the training events, thus the synaptic resistance (i.e., the synaptic weight) is not affected outside the training process.
    • 本公开的某些实施例支持在生物启发网络中训练突触的技术。 只有一个基于忆阻器的设备可以用作一对神经元之间的突触连接。 突触体重的训练可以用低电流消耗来实现。 所提出的突触训练电路可以由多个输入/输出连接共享,而每个神经元电路只能使用一个数字实现的脉宽调制(PWM)发生器来产生突触训练脉冲。 只有三个阶段的慢时钟可以用于神经元到神经元通信和突触训练。 还可以生成一些特殊的控制信号来设置突触训练事件。 通过这些信号,突触训练电路可以在训练事件之外处于高阻抗状态,因此在训练过程之外不会影响突触电阻(即突触重量)。