公开(公告)号：US20150046383A1

公开(公告)日：2015-02-12

申请号：US14167727

申请日：2014-01-29

Applicant: QUALCOMM Incorporated

Inventor： Jason Frank HUNZINGER ,  Victor Hokkiu CHAN

IPC: G06N3/08

CPC classification number: G06N3/049

Abstract: Methods and apparatus are provided for implementing behavioral homeostasis in artificial neurons that use a dynamical spiking neuron model. The homeostatic mechanism may be driven by neuron state, rather than by neuron spiking rate, and this mechanism may drive changes to the neuron temporal dynamics, rather than to contributions of input or weights. As a result, certain aspects of the present disclosure are a more natural fit with spiking neural networks and have many functional and computational advantages. One example method for implementing homeostasis of an artificial nervous system generally includes determining one or more state variables of a neuron model used by an artificial neuron, based at least in part on dynamics of the neuron model; determining one or more conditions based at least in part on the state variables; and adjusting the dynamics based at least in part on the conditions.

Abstract translation: 提供了用于在使用动力学刺激神经元模型的人造神经元中实现行为动态平衡的方法和装置。 稳态机制可以由神经元状态驱动，而不是由神经元峰值速率驱动，并且这种机制可以驱动神经元时间动力学的变化，而不是输入或权重的贡献。 结果，本公开的某些方面与掺加神经网络更为自然，并且具有许多功能和计算的优点。 用于实现人造神经系统的体内平衡的一个示例性方法通常包括至少部分地基于神经元模型的动力学来确定由人造神经元使用的神经元模型的一个或多个状态变量; 至少部分地基于状态变量确定一个或多个条件; 并且至少部分地基于条件来调整动力学。

公开(公告)号：US20150220829A1

公开(公告)日：2015-08-06

申请号：US14172742

申请日：2014-02-04

Applicant: QUALCOMM INCORPORATED

Inventor： Jason Frank HUNZINGER ,  Jeffrey Alexander LEVIN

IPC: G06N3/02

CPC classification number: G06N3/049

Abstract: A method of approximating delay for postsynaptic potentials includes receiving a postsynaptic potential. The method further includes filtering the postsynaptic potential to approximate a delayed delivery of the postsynaptic potential.

Abstract translation: 逼近突触后电位延迟的方法包括接收突触后电位。 该方法还包括过滤突触后电位以近似突触后电位的延迟递送。

公开(公告)号：US20150178617A1

公开(公告)日：2015-06-25

申请号：US14139732

申请日：2013-12-23

Applicant: QUALCOMM Incorporated

Inventor： Michael-David Nakayoshi CANOY ,  Jason Frank HUNZINGER

IPC: G06N3/02

CPC classification number: G06N3/049

Abstract: A method of monitoring a neural network includes monitoring activity of the neural network. The method also includes detecting a condition based on the activity. The method further includes performing an exception event based on the detected condition.

Abstract translation: 监测神经网络的方法包括监测神经网络的活动。 该方法还包括基于活动来检测条件。 该方法还包括基于检测到的条件执行异常事件。

公开(公告)号：US20160260012A1

公开(公告)日：2016-09-08

申请号：US15157035

申请日：2016-05-17

Applicant: QUALCOMM Incorporated

Inventor： Jason Frank HUNZINGER ,  Ryan Michael CAREY ,  Victor Hokkiu CHAN ,  Casimir Matthew WIERZYNSKI

IPC: G06N3/063 ,  G06N3/08

CPC classification number: G06N3/063 ,  G06N3/049 ,  G06N3/08 ,  G06N3/088

Abstract: A method for creating and maintaining short-term memory using short-term plasticity, includes changing a gain of a synapse based on pre synaptic spike activity without regard to postsynaptic spike activity. The method also includes calculating the gain based on a continuously updated synaptic state variable associated with the short-term plasticity.

Abstract translation: 使用短期可塑性创建和维持短期记忆的方法包括基于突触前突变活动改变突触的增益，而不考虑突触后的尖峰活动。 该方法还包括基于与短期可塑性相关联的连续更新的突触状态变量来计算增益。

公开(公告)号：US20150081607A1

公开(公告)日：2015-03-19

申请号：US14157143

申请日：2014-01-16

Applicant: QUALCOMM Incorporated

Inventor： Jason Frank HUNZINGER ,  Michael-David Nakayoshi CANOY ,  Paul Edward BENDER ,  Victor Hokkiu CHAN ,  Gina Marcela ESCOBAR MORA

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/04 ,  G06N3/049 ,  G06N3/08 ,  G06N3/082

Abstract: Methods and apparatus are provided for implementing structural plasticity in an artificial nervous system. One example method for altering a structure of an artificial nervous system generally includes determining a synapse in the artificial nervous system for reassignment, determining a first artificial neuron and a second artificial neuron for connecting via the synapse, and reassigning the synapse to connect the first artificial neuron with the second artificial neuron. Another example method for operating an artificial nervous system, generally includes determining a synapse in the artificial nervous system for assignment; determining a first artificial neuron and a second artificial neuron for connecting via the synapse, wherein at least one of the synapse or the first and second artificial neurons are determined randomly or pseudo-randomly; and assigning the synapse to connect the first artificial neuron with the second artificial neuron.

Abstract translation: 提供了在人造神经系统中实现结构可塑性的方法和装置。 用于改变人造神经系统的结构的一个示例性方法通常包括确定用于重新分配的人造神经系统中的突触，确定第一人造神经元和第二人造神经元以经由突触连接，以及重新分配突触以连接第一人工神经元 神经元与第二个人造神经元。 用于操作人造神经系统的另一示例性方法通常包括确定用于分配的人造神经系统中的突触; 确定经由所述突触连接的第一人造神经元和第二人造神经元，其中所述突触或所述第一和第二人造神经元中的至少一个被随机地或伪随机地确定; 并分配突触将第一人工神经元与第二人造神经元连接。

公开(公告)号：US20150220831A1

公开(公告)日：2015-08-06

申请号：US14174685

申请日：2014-02-06

Applicant: QUALCOMM Incorporated

Inventor： Jason Frank HUNZINGER ,  Ryan CAREY ,  Victor Hokkiu CHAN ,  Casimir Matthew WIERZYNSKI

IPC: G06N3/08

CPC classification number: G06N3/063 ,  G06N3/049 ,  G06N3/08 ,  G06N3/088

Abstract: A method for creating and maintaining short term memory using short term plasticity, includes changing a gain of a synapse based on presynaptic spike activity without regard to postsynaptic spike activity. The method also includes calculating the gain based on a continuously updated synaptic state variable associated with the short term plasticity.

Abstract translation: 使用短期可塑性创建和维持短期记忆的方法包括基于突触前穗活动改变突触的增益，而不考虑突触后穗活动。 该方法还包括基于与短期可塑性相关联的连续更新的突触状态变量来计算增益。

公开(公告)号：US20150213356A1

公开(公告)日：2015-07-30

申请号：US14163921

申请日：2014-01-24

Applicant: Qualcomm Incorporated

Inventor： Michael-David Nakayoshi CANOY ,  Yinyin LIU ,  Bardia Fallah BEHABADI ,  Venkat RANGAN ,  Jason Frank HUNZINGER

IPC: G06N3/08

CPC classification number: G06N3/08 ,  G06N3/049

Abstract: A method for transmitting values in a neural network includes obtaining a parameter value. The method also includes encoding the parameter value based on at least one value used by a neuron. The encoding is based on a spike to be transmitted via a spike channel.

Abstract translation: 用于在神经网络中传输值的方法包括获得参数值。 该方法还包括基于由神经元使用的至少一个值对参数值进行编码。 编码是基于要通过尖峰通道传输的尖峰。

公开(公告)号：US20150120627A1

公开(公告)日：2015-04-30

申请号：US14160128

申请日：2014-01-21

Applicant: QUALCOMM Incorporated

Inventor： Jason Frank HUNZINGER ,  Thomas Jiaqian ZHENG

IPC: G06N3/08

CPC classification number: G06N3/08 ,  G06N3/049 ,  G06N3/088 ,  G06N7/005

Abstract: Methods and apparatus are provided for causal learning in which logical causes of events are determined based, at least in part, on causal saliency. One example method for causal learning generally includes observing one or more events with an apparatus, wherein the events are defined as occurrences at particular relative times; selecting a subset of the events based on one or more criteria; and determining a logical cause of at least one of the events based on the selected subset.

Abstract translation: 提供了用于因果学习的方法和装置，其中事件的逻辑原因至少部分地基于因果显着性来确定。 用于因果学习的一个示例性方法通常包括用设备观察一个或多个事件，其中事件被定义为在特定相对时间的出现; 基于一个或多个标准来选择事件的子集; 以及基于所选择的子集来确定所述事件中的至少一个的逻辑原因。

公开(公告)号：US20150052094A1

公开(公告)日：2015-02-19

申请号：US14167752

申请日：2014-01-29

Applicant: QUALCOMM Incorporated

Inventor： Jason Frank HUNZINGER ,  Jeffrey Alexander LEVIN

IPC: G06N3/04

CPC classification number: G06N3/049 ,  G06N3/04

Abstract: Methods and apparatus are provided for inferring and accounting for missing post-synaptic events (e.g., a post-synaptic spike that is not associated with any pre-synaptic spikes) at an artificial neuron and adjusting spike-timing dependent plasticity (STDP) accordingly. One example method generally includes receiving, at an artificial neuron, a plurality of pre-synaptic spikes associated with a synapse, tracking a plurality of post-synaptic spikes output by the artificial neuron, and determining at least one of the post-synaptic spikes is associated with none of the plurality of pre-synaptic spikes. According to certain aspects, determining inferring missing post-synaptic events may be accomplished by using a flag, counter, or other variable that is updated on post-synaptic firings. If this post-ghost variable changes between pre-synaptic-triggered adjustments, then the artificial nervous system can determine there was a missing post-synaptic pairing.

Abstract translation: 提供了用于推断和计算在人造神经元处丢失的突触后事件（例如，与突触前尖峰之间不相关的突触后尖峰）并相应地调整尖峰时序依赖性可塑性（STDP）的方法和装置。 一个示例性方法通常包括在人造神经元处接收与突触相关联的多个突触前尖峰，跟踪由人造神经元输出的多个突触后尖峰，并且确定突触后尖峰中的至少一个是 与多个突触前尖峰中的任一个相关联。 根据某些方面，确定推断缺失的突触后事件可以通过使用在突触后发射上更新的标志，计数器或其他变量来实现。 如果这个后幽灵变量在突触前触发的调整之间变化，则人造神经系统可以确定缺少突触后配对。