公开(公告)号：WO2015034640A3

公开(公告)日：2015-05-14

申请号：PCT/US2014051044

申请日：2014-08-14

Applicant: QUALCOMM INC

Inventor： CANOY MICHAEL-DAVID NAKAYOSHI ,  BELL II WILLIAM RICHARD ,  KINTADA RAMAKRISHNA ,  RANGAN VENKAT

IPC: G06N3/04 ,  G06F11/30 ,  G06F11/36 ,  G06N3/06 ,  G06N3/08 ,  G06N3/10

CPC classification number: G06N3/10 ,  G06F11/302 ,  G06F11/3636 ,  G06N3/049 ,  G06N3/08

Abstract: Methods and apparatus are provided for using a breakpoint determination unit to examine an artificial nervous system. One example method generally includes operating at least a portion of the artificial nervous system; using the breakpoint determination unit to detect that a condition exists based at least in part on monitoring one or more components in the artificial nervous system; and at least one of suspending, examining, modifying, or flagging the operation of the at least the portion of the artificial nervous system, based at least in part on the detection.

Abstract translation: 提供了使用断点确定单元检查人造神经系统的方法和设备。 一个示例性方法通常包括操作人造神经系统的至少一部分; 使用所述断点确定单元至少部分地基于监测所述人造神经系统中的一个或多个组件来检测所述条件存在; 以及至少部分基于所述检测来暂停，检查，修改或标记所述人造神经系统的所述至少一部分的操作中的至少一者。

公开(公告)号：WO2015023425A3

公开(公告)日：2015-05-14

申请号：PCT/US2014048605

申请日：2014-07-29

Applicant: QUALCOMM INC

Inventor： CANOY MICHAEL-DAVID NAKAYOSHI ,  LIU YINYIN ,  SARAH ANTHONY ,  MILNER ADRIENNE

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/049

Abstract: Methods and apparatus are provided for training a neural device having an artificial nervous system by modulating at least one training parameter during the training. One example method for training a neural device having an artificial nervous system generally includes observing the neural device in a training environment and modulating at least one training parameter based at least in part on the observing. For example, the training apparatus described herein may modify the neural device's internal learning mechanisms (e.g., spike rate, learning rate, neuromodulators, sensor sensitivity, etc.) and/or the training environment's stimuli (e.g., move a flame closer to the device, make the scene darker, etc.). In this manner, the speed with which the neural device is trained (i.e., the training rate) may be significantly increased compared to conventional neural device training systems.

Abstract translation: 提供了用于通过在训练期间调制至少一个训练参数来训练具有人造神经系统的神经装置的方法和装置。 用于训练具有人造神经系统的神经装置的一个示例方法通常包括在训练环境中观察神经装置并且至少部分地基于观察来调制至少一个训练参数。 例如，本文描述的训练装置可以修改神经装置的内部学习机制（例如，尖峰速率，学习速率，神经调节器，传感器灵敏度等）和/或训练环境的刺激（例如，使火焰更靠近装置 ，使场景变暗等）。 以这种方式，与传统的神经装置训练系统相比，神经装置训练的速度（即，训练速率）可以显着增加。

公开(公告)号：WO2014190340A3

公开(公告)日：2015-04-23

申请号：PCT/US2014039469

申请日：2014-05-24

Applicant: QUALCOMM INC

Inventor： CANOY MICHAEL-DAVID NAKAYOSHI ,  SPRIGG STEPHEN ALTON

IPC: G06N99/00 ,  H04L29/08

CPC classification number: G06N99/005

Abstract: Various embodiments for modifying learning capabilities within a decentralized system of learning devices, a method including receiving, at a learning device, a signal from a nearby device, determining whether the received signal is a learning modifier signal based on data within the received signal, and modifying one or more of the learning capabilities in response to determining that the received signal is the learning modifier signal. The method may further include determining whether subsequent learning modifier signals are received, and resetting the modified one or more of the learning capabilities in response to determining that the subsequent learning modifier signals are not received. Modifying learning capabilities may include enabling or disabling a learning mode of the learning device and/or adjusting values of variables used to calculate trigger weights of reflexes. When subsequent learning modifier signals are not received, the learning device may reset modified learning capabilities.

Abstract translation: 用于修改分散式学习装置系统中的学习能力的各种实施例，一种方法，包括在学习装置处接收来自附近装置的信号，基于接收到的信号内的数据确定接收到的信号是否是学习修改器信号;以及 响应于确定所接收的信号是学习修改器信号来修改学习能力中的一个或多个。 该方法还可以包括确定是否接收后续学习修改器信号，以及响应于确定未接收到后续学习修改器信号来重置所修改的一个或多个学习能力。 修改学习功能可以包括启用或禁用学习设备的学习模式和/或调整用于计算反射的触发权重的变量的值。 当未接收到随后的学习修改器信号时，学习设备可以重置修改的学习能力。

公开(公告)号：WO2015038311A3

公开(公告)日：2015-07-02

申请号：PCT/US2014052255

申请日：2014-08-22

Applicant: QUALCOMM INC

Inventor： CANOY MICHAEL-DAVID NAKAYOSHI ,  BENDER PAUL EDWARD ,  CHAN VICTOR HOKKIU ,  ESCOBAR MORA GINA MARCELA ,  HUNZINGER JASON FRANK

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: 提供了用于在人造神经系统中实现结构可塑性的方法和设备。 用于改变人造神经系统的结构的一个示例方法通常包括：确定用于重新分配的人造神经系统中的突触;确定用于经由突触连接的第一人造神经元和第二人造神经元;以及重新分配突触以连接第一人造神经元 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方法通常包括：确定人工神经系统中的突触以进行分配; 确定用于经由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人造神经元和所述第二人造神经元中的至少一个是随机地或伪随机地确定的; 并分配突触以连接第一人造神经元和第二人造神经元。

公开(公告)号：WO2014190336A3

公开(公告)日：2015-04-16

申请号：PCT/US2014039465

申请日：2014-05-24

Applicant: QUALCOMM INC

Inventor： CANOY MICHAEL-DAVID NAKAYOSHI

IPC: G06N99/00

CPC classification number: G06N99/005

Abstract: An embodiment method for continuous configuration of learning devices includes operations for storing, by a learning device within a decentralized system of a plurality of learning devices, events obtained while in a monitoring mode, activating a triggered mode for a reflex when at least one of the stored events corresponds to a trigger pattern, determining whether the reflex has a trigger weight exceeding a trigger weight threshold, conducting the predetermined action associated with the reflex when the trigger weight exceeds the trigger weight threshold, obtaining at least one additional event while in the triggered mode, adjusting the trigger weight of the reflex when the at least one additional event corresponds to a correction pattern or a reward pattern occurring in response to conducting the predetermined action, and creating a second reflex when the at least one additional event does not correspond to a known pattern.

Abstract translation: 用于学习设备的连续配置的实施例方法包括用于由多个学习设备的分散系统内的学习设备存储在监视模式下获得的事件的操作，当在至少一个学习设备中的至少一个时，激活用于反射的触发模式 存储的事件对应于触发模式，确定反射是否具有超过触发权重阈值的触发权重，当触发权重超过触发权重阈值时执行与反射相关联的预定动作，在触发时获得至少一个附加事件 模式，当所述至少一个附加事件对应于响应于执行所述预定动作而发生的校正模式或奖励模式时，调整所述反射的所述触发权重，以及当所述至少一个附加事件不对应于 一种已知的模式。

公开(公告)号：WO2014190338A3

公开(公告)日：2015-04-09

申请号：PCT/US2014039467

申请日：2014-05-24

Applicant: QUALCOMM INC

Inventor： CANOY MICHAEL-DAVID NAKAYOSHI ,  KONERTZ ANNE KATRIN ,  CHAU KIET ,  MOHAN SIDDHARTH

IPC: G06N99/00 ,  G09B5/00

CPC classification number: G09B5/00 ,  G06N99/005

Abstract: Various embodiments for conducting proxy teaching for learning devices within a decentralized system, including an embodiment method with operations for obtaining, by a teacher signaling device, objectives data related to activities of one or more of the learning devices, generating, by the teacher signaling device, teaching routines based on the obtained objectives data, and broadcasting, by the teacher signaling device, teaching signals configured to teach one or more of the learning devices based on the generated teaching routines. Other embodiments may obtain objectives data by requesting reflex information from the learning devices or intercepting event report messages transmitted by the learning devices. Other embodiments may include broadcasting discovery signals to identify nearby learning devices and modifying teaching routines when objectives of the generated teaching routines cannot be achieved. Other embodiments may include transmitting an authorization request to a user device to determine whether to broadcast teaching signals.

Abstract translation: 用于进行分散式系统内的学习装置的代理教学的各种实施例，包括具有操作的实施方式的方法，该操作由教师信号装置获取与一个或多个学习装置的活动相关的目标数据，由教师信号装置 基于所获得的目标数据的教学例程，以及由教师信号装置根据生成的教学例程，配置成教导一个或多个学习装置的教学信号。 其他实施例可以通过从学习设备请求反射信息或截取学习设备发送的事件报告消息来获得目标数据。 其他实施例可以包括广播发现信号以识别附近的学习设备，并且当不能实现生成的教学例程的目标时修改教学例程。 其他实施例可以包括向用户设备发送授权请求以确定是否广播教学信号。

公开(公告)号：WO2014190339A3

公开(公告)日：2015-03-26

申请号：PCT/US2014039468

申请日：2014-05-24

Applicant: QUALCOMM INC

Inventor： CANOY MICHAEL-DAVID NAKAYOSHI

IPC: G06N99/00

CPC classification number: H04L67/10 ,  G06N99/005

Abstract: An embodiment delay device for use within a decentralized system of learning device delays broadcast messages to introduce a time shift into events. The delay device may receive a first message from a triggering device, generate a first pattern using at least a first event based on the received first message, determine whether the first pattern matches a known trigger pattern, wait a predetermined delay period in response to determining that the first pattern matches the known trigger pattern, and broadcast a second message in response to the predetermined delay period expiring. Delay periods may be user-configurable, such as via user inputs (e.g., dials, sliders, etc.) or learned based on messages from responding devices. The second message may be similar to the first message or a distinct message indicating the elapse of the delay period.

Abstract translation: 在分散式学习设备系统内使用的实施例延迟装置延迟广播消息以将时移引入事件。 所述延迟装置可以从触发装置接收第一消息，基于所接收的第一消息，使用至少第一事件生成第一模式，确定所述第一模式是否与已知触发模式匹配，响应于确定，等待预定的延迟周期 第一模式与已知的触发模式匹配，并且响应于预定的延迟时段到期而广播第二消息。 延迟周期可以是用户可配置的，例如通过用户输入（例如，拨号盘，滑块等）或基于来自响应设备的消息学习。 第二消息可以类似于第一消息或指示延迟时间段经过的明确消息。

公开(公告)号：WO02062025A3

公开(公告)日：2002-10-17

申请号：PCT/US0203015

申请日：2002-01-30

Applicant: QUALCOMM INC

Inventor： BENDER PAUL E ,  CANOY MICHAEL-DAVID NAKAYOSHI ,  MOHANTY BIBHU ,  PANKAJ RAJESH K ,  TSYBAKOV BORIS S

IPC: H04W28/16 ,  H04L29/08 ,  H04W48/06 ,  H04L12/56

CPC classification number: H04L67/16 ,  H04L67/14 ,  H04L69/329

Abstract: In a communication system (1400) for communication of data, a method and apparatus provide for detecting a request for opening a connection for a user (1407) for communication of data, selecting an open connection, releasing the selected open connection, and allocating, to the user (1407), communication resources corresponding to resources released based on releasing the selected open connection. In accordance with an embodiment, the selected open connection is in an idle open state.

Abstract translation: 在用于数据通信的通信系统（1400）中，提供了一种方法和设备，用于检测用于打开用户的连接的请求（1407），用于数据通信，选择打开的连接，释放所选的打开的连接， 向用户（1407）发送与基于释放所选打开连接而释放的资源相对应的通信资源。 根据一个实施例，所选打开连接处于空闲打开状态。