ARTIFICIAL NEURONS AND SPIKING NEURONS WITH ASYNCHRONOUS PULSE MODULATION
    1.
    发明申请
    ARTIFICIAL NEURONS AND SPIKING NEURONS WITH ASYNCHRONOUS PULSE MODULATION 审中-公开
    人工神经元和神经元与异常脉冲调制

    公开(公告)号:WO2016022241A1

    公开(公告)日:2016-02-11

    申请号:PCT/US2015/039396

    申请日:2015-07-07

    CPC classification number: G06N3/08 G06N3/04 G06N3/049

    Abstract: A method for configuring an artificial neuron includes receiving a set of input spike trains comprising asynchronous pulse modulation coding representations. The method also includes generating output spikes representing a similarity between the set of input spike trains and a spatial-temporal filter.

    Abstract translation: 一种用于配置人造神经元的方法包括接收包括异步脉冲调制编码表示的一组输入尖峰序列。 该方法还包括产生表示在该组输入尖峰火车和空间 - 时间滤波器之间的相似性的输出尖峰。

    PIECEWISE LINEAR NEURON MODELING
    2.
    发明申请
    PIECEWISE LINEAR NEURON MODELING 审中-公开
    分段线性神经元建模

    公开(公告)号:WO2014081562A1

    公开(公告)日:2014-05-30

    申请号:PCT/US2013/068537

    申请日:2013-11-05

    Abstract: Methods and apparatus for piecewise linear neuron modeling and implementing artificial neurons in an artificial nervous system based on linearized neuron models. One example method for operating an artificial neuron generally includes determining that a first state of the artificial neuron is within a first region; determining a second state of the artificial neuron based at least in part on a first set of linear equations, wherein the first set of linear equations is based at least in part on a first set of parameters corresponding to the first region; determining that the second state of the artificial neuron is within a second region; and determining a third state of the artificial neuron based at least in part on a second set of linear equations, wherein the second set of linear equations is based at least in part on a second set of parameters corresponding to the second region.

    Abstract translation: 用于基于线性化神经元模型的分段线性神经元建模和在人工神经系统中实施人造神经元的方法和装置 用于操作人造神经元的一个示例性方法通常包括确定人造神经元的第一状态在第一区域内; 至少部分基于第一线性方程组来确定所述人造神经元的第二状态,其中所述第一线性方程组至少部分地基于对应于所述第一区域的第一组参数; 确定所述人造神经元的所述第二状态在第二区域内; 以及至少部分地基于第二线性方程组来确定所述人造神经元的第三状态,其中所述第二线性方程组至少部分地基于对应于所述第二区域的第二参数集合。 >

    PIECEWISE LINEAR NEURON MODELING
    3.
    发明申请
    PIECEWISE LINEAR NEURON MODELING 审中-公开
    PIECEWISE线性神经元建模

    公开(公告)号:WO2014081561A1

    公开(公告)日:2014-05-30

    申请号:PCT/US2013/068531

    申请日:2013-11-05

    Abstract: Methods and apparatus for piecewise linear neuron modeling and implementing one or more artificial neurons in an artificial nervous system based on one or more linearized neuron models. One example method (for implementing a combination of a plurality of neuron models in a system of neural processing units) generally includes loading parameters for a first neuron model selected from the plurality of neuron models into a first neural processing unit, determining a first state of the first neural processing unit based at least in part on the parameters for the first neuron model, and determining a second state of the first neural processing unit based at least in part on the parameters for the first neuron model and on the first state. This method may also include updating the plurality of neuron models (e.g., by adding, deleting, or adjusting parameters for the first neuron model or another neuron model).

    Abstract translation: 基于一个或多个线性化神经元模型的分段线性神经元建模和实现人造神经系统中的一个或多个人造神经元的方法和装置。 一个示例性方法(用于实现神经处理单元的系统中的多个神经元模型的组合)通常包括将从多个神经元模型中选择的第一神经元模型的参数加载到第一神经处理单元中,确定第一状态 所述第一神经处理单元至少部分地基于所述第一神经元模型的参数,以及至少部分地基于所述第一神经元模型的参数和所述第一状态来确定所述第一神经处理单元的第二状态。 该方法还可以包括更新多个神经元模型(例如,通过添加,删除或调整第一神经元模型或另一个神经元模型的参数)。

    ENHANCEMENTS FOR MULTI-MODE SYSTEM SELECTION (MMSS) AND MMSS SYSTEM PRIORITY LISTS (MSPLS)
    4.
    发明申请
    ENHANCEMENTS FOR MULTI-MODE SYSTEM SELECTION (MMSS) AND MMSS SYSTEM PRIORITY LISTS (MSPLS) 审中-公开
    多模式系统选择(MMSS)和MMSS系统优先级(MSPLS)的增强

    公开(公告)号:WO2011011457A1

    公开(公告)日:2011-01-27

    申请号:PCT/US2010/042659

    申请日:2010-07-20

    CPC classification number: H04W48/20

    Abstract: A mobile device or access terminal of a wireless wide area network (WWAN) communication system is provisioned for Multi-Mode System Selection (MMSS) wherein an MMSS System Priority List (MSPL) is used with respect to the underlying system selection priority list (e.g., Private Land Mobile Network (PLMN) list). Relating a current location to one or more entries in an MMSS Location Associated Priority List (MLPLs) enables scaling a range of entries in the PLMN list, indicating whether the MSPL apply to the entire list of PLMNs stored in an access terminal or to some subset of the PLMN List. Similarly, the present innovation addresses whether the MSPL applies to the entire Preferred Roaming List (PRL) or some subset of a geo-spatial location (GEO) area.

    Abstract translation: 提供无线广域网(WWAN)通信系统的移动设备或接入终端用于多模式系统选择(MMSS),其中相对于基础系统选择优先级列表使用MMSS系统优先级列表(MSPL)(例如, ,私有移动网络(PLMN)列表)。 将当前位置与MMSS位置关联优先级列表(MLPL)中的一个或多个条目关联使得能够缩放PLMN列表中的条目范围,指示MSPL是否适用于存储在接入终端中的整个PLMN列表或某些子集 的PLMN列表。 类似地,本创新解决了MSPL是否适用于整个首选漫游列表(PRL)或地理空间位置(GEO)区域的某个子集。

    EVENT-DRIVEN TEMPORAL CONVOLUTION FOR ASYNCHRONOUS PULSE-MODULATED SAMPLED SIGNALS
    5.
    发明申请
    EVENT-DRIVEN TEMPORAL CONVOLUTION FOR ASYNCHRONOUS PULSE-MODULATED SAMPLED SIGNALS 审中-公开
    用于异步脉冲调制采样信号的事件驱动时间演变

    公开(公告)号:WO2016036565A1

    公开(公告)日:2016-03-10

    申请号:PCT/US2015/047010

    申请日:2015-08-26

    CPC classification number: G06N3/08 G06F17/15 G06N3/04 G06N3/049

    Abstract: A method of processing asynchronous event-driven input samples of a continuous time signal, includes calculating a convolutional output directly from the event-driven input samples. The convolutional output is based on an asynchronous pulse modulated (APM) encoding pulse. The method further includes interpolating output between events.

    Abstract translation: 处理连续时间信号的异步事件驱动输入样本的方法包括直接从事件驱动输入样本计算卷积输出。 卷积输出基于异步脉冲调制(APM)编码脉冲。 该方法还包括在事件之间内插输出。

    ASYNCHRONOUS PULSE MODULATION FOR THRESHOLD-BASED SIGNAL CODING
    6.
    发明申请
    ASYNCHRONOUS PULSE MODULATION FOR THRESHOLD-BASED SIGNAL CODING 审中-公开
    用于基于阈值信号编码的异步脉冲调制

    公开(公告)号:WO2015199844A1

    公开(公告)日:2015-12-30

    申请号:PCT/US2015/031568

    申请日:2015-05-19

    Abstract: A method of signal processing includes comparing an input signal with one or more positive threshold values and one or more negative threshold values. The method also includes generating an output signal based on the comparison of the input signal with the positive threshold(s) and negative threshold(s). The method further includes feeding the output signal back into a decaying reconstruction filter to create a reconstructed signal and combining the reconstructed signal with the input signal.

    Abstract translation: 信号处理的方法包括将输入信号与一个或多个正阈值和一个或多个负阈值进行比较。 该方法还包括基于输入信号与正阈值和负阈值的比较来产生输出信号。 该方法还包括将输出信号反馈回衰减重构滤波器以产生重构信号并将重构信号与输入信号组合。

    PIECEWISE LINEAR NEURON MODELING
    10.
    发明公开
    PIECEWISE LINEAR NEURON MODELING 审中-公开
    分段线性神经建模

    公开(公告)号:EP2923309A1

    公开(公告)日:2015-09-30

    申请号:EP13795358.4

    申请日:2013-11-05

    Abstract: Methods and apparatus for piecewise linear neuron modeling and implementing one or more artificial neurons in an artificial nervous system based on one or more linearized neuron models. One example method (for implementing a combination of a plurality of neuron models in a system of neural processing units) generally includes loading parameters for a first neuron model selected from the plurality of neuron models into a first neural processing unit, determining a first state of the first neural processing unit based at least in part on the parameters for the first neuron model, and determining a second state of the first neural processing unit based at least in part on the parameters for the first neuron model and on the first state. This method may also include updating the plurality of neuron models (e.g., by adding, deleting, or adjusting parameters for the first neuron model or another neuron model).

Patent Agency Ranking