公开(公告)号：US20160034812A1

公开(公告)日：2016-02-04

申请号：US14527679

申请日：2014-10-29

Applicant: QUALCOMM Incorporated

Inventor： Sarah Paige GIBSON ,  Yinyin LIU

IPC: G06N3/08

CPC classification number: G06N3/08 ,  G06N3/049

Abstract: A method for configuring long short-term memory (LSTM) in a spiking neural network includes decoding input spikes into analog values within the LSTM. The method further includes implementing the LSTM based on an encoded representation of the analog values. The implementing can include encoding the analog values using base expansive coding, rate coding, latency coding or synaptic weight coding.

Abstract translation: 一种在尖峰神经网络中配置长时间短记忆（LSTM）的方法包括将输入尖峰解码为LSTM内的模拟值。 该方法还包括基于模拟值的编码表示来实现LSTM。 该实现可以包括使用基本扩展编码，速率编码，等待时间编码或突触权重编码对模拟值进行编码。

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：US20150212861A1

公开(公告)日：2015-07-30

申请号：US14163893

申请日：2014-01-24

Applicant: QUALCOMM Incorporated

Inventor： Michael-David Nakayoshi CANOY ,  Yinyin LIU ,  Victor Hokkiu CHAN ,  Michael CAMPOS ,  Jeffrey Alexander LEVIN ,  Casimir Matthew WIERZYNSKI

IPC: G06F9/52 ,  G06N3/08

CPC classification number: G06F9/52 ,  G06N3/049 ,  G06N3/063 ,  G06N3/08 ,  G06N20/00

Abstract: Values are synchronized across processing blocks in a neural network by encoding spikes in a first processing block with a value to be shared across the neural network. The spikes may be transmitted to a second processing block in the neural network via an interblock interface. The received spikes are decoded in the second processing block so as to generate a value that is synchronized with the value of the first processing block.

Abstract translation: 通过在第一处理块中对尖峰进行编码以跨神经网络共享的值来在神经网络中的处理块之间同步数值。 尖峰可以经由帧间接口发送到神经网络中的第二处理块。 接收的尖峰在第二处理块中解码，以产生与第一处理块的值同步的值。

公开(公告)号：US20150052093A1

公开(公告)日：2015-02-19

申请号：US14079181

申请日：2013-11-13

Applicant: QUALCOMM Incorporated

Inventor： Michael-David Nakayoshi CANOY ,  Yinyin LIU ,  Anthony SARAH ,  Adrienne MILNER

IPC: G06N3/08

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性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，将火焰移动到设备附近 ，使场景更暗等）。 以这种方式，与传统的神经元装置训练系统相比，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：US20150269481A1

公开(公告)日：2015-09-24

申请号：US14513155

申请日：2014-10-13

Applicant: QUALCOMM Incorporated

Inventor： Venkata Sreekanta Reddy ANNAPUREDDY ,  David Jonathan JULIAN ,  Regan Blythe TOWAL ,  Yinyin LIU

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/0445 ,  G06N3/0481 ,  G06N3/049

Abstract: Differential encoding in a neural network includes predicting an activation value for a neuron in the neural network based on at least one previous activation value for the neuron. The encoding further includes encoding a value based on a difference between the predicted activation value and an actual activation value for the neuron in the neural network.

Abstract translation: 神经网络中的差分编码包括基于神经元的至少一个先前激活值来预测神经网络中神经元的激活值。 编码还包括基于预测的激活值和神经网络中的神经元的实际激活值之间的差来编码值。

公开(公告)号：US20150286925A1

公开(公告)日：2015-10-08

申请号：US14248211

申请日：2014-04-08

Applicant: QUALCOMM Incorporated

Inventor： Jeffrey Alexander LEVIN ,  Yinyin LIU ,  Sandeep PENDYAM ,  Michael CAMPOS

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/049 ,  G06N3/08

Abstract: A method for maintaining a state variable in a synapse of a neural network includes maintaining a state variable in an axon. The state variable in the axon may be updated based on an occurrence of a first predetermined event. The method also includes updating the state variable in the synapse based on the state variable in the axon and an occurrence of a second predetermined event.

Abstract translation: 维持神经网络突触状态变量的方法包括维持轴突中的状态变量。 可以基于第一预定事件的发生来更新轴突中的状态变量。 该方法还包括基于轴突中的状态变量和第二预定事件的发生来更新突触中的状态变量。

公开(公告)号：US20150242746A1

公开(公告)日：2015-08-27

申请号：US14325169

申请日：2014-07-07

Applicant: QUALCOMM Incorporated

Inventor： Naveen Gandham RAO ,  Michael CAMPOS ,  Yinyin LIU

IPC: G06N3/08

Abstract: A method of dynamically modifying target selection with a neural network includes dynamically modifying a selection function by controlling an amount of imbalance of connections in the neural network. A selected neuron represents one of multiple candidate targets.

Abstract translation: 用神经网络动态修改目标选择的方法包括通过控制神经网络中的连接的不平衡量来动态修改选择功能。 选择的神经元代表多个候选目标之一。

公开(公告)号：US20150161506A1

公开(公告)日：2015-06-11

申请号：US14260140

申请日：2014-04-23

Applicant: QUALCOMM Incorporated

Inventor： Jeffrey Alexander LEVIN ,  Yinyin LIU ,  Sarah Paige GIBSON ,  Michael CAMPOS ,  Vikram GUPTA ,  Victor Hokkiu CHAN ,  Edward Hanyu LIAO ,  Erik Christopher MALONE

IPC: G06N3/08

CPC classification number: G06N3/08 ,  G06N3/049

Abstract: Methods and apparatus are provided for effecting modulation using global scalar values in a spiking neural network. One example method for operating an artificial nervous system generally includes determining one or more updated values for artificial neuromodulators to be used by a plurality of entities in a neuron model and providing the updated values to the plurality of entities.

Abstract translation: 提供了方法和装置，用于在加标神经网络中使用全局标量值进行调制。 用于操作人造神经系统的一个示例性方法通常包括确定将由神经元模型中的多个实体使用的人造神经调节器的一个或多个更新值，并向多个实体提供更新的值。