公开(公告)号：US20160055409A1

公开(公告)日：2016-02-25

申请号：US14528890

申请日：2014-10-30

Applicant: QUALCOMM Incorporated

Inventor： Somdeb MAJUMDAR ,  Regan Blythe TOWAL ,  Sachin Subhash TALATHI ,  David Jonathan JULIAN ,  Venkata Sreekanta Reddy ANNAPUREDDY

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04 ,  G06N3/0427 ,  G06N3/049 ,  G06N7/005

Abstract: A method for classifying an object includes applying multiple confidence values to multiple objects. The method also includes determining a metric based on the multiple confidence values. The method further includes determining a classification of a first object from the multiple objects based on a knowledge-graph when the metric is above a threshold.

Abstract translation: 用于分类对象的方法包括将多个置信度值应用于多个对象。 该方法还包括基于多个置信度值来确定度量。 该方法还包括当度量高于阈值时，基于知识图来确定来自多个对象的第一对象的分类。

公开(公告)号：US20170091619A1

公开(公告)日：2017-03-30

申请号：US15081780

申请日：2016-03-25

Applicant: QUALCOMM Incorporated

Inventor： Regan Blythe TOWAL ,  David Jonathan JULIAN

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/084 ,  G06K9/4628 ,  G06N3/0472

Abstract: The balance of training data between classes for a machine learning model is modified. Adjustments are made at the gradient stage where selective backpropagation is utilized to modify a cost function to adjust or selectively apply the gradient based on the class example frequency in the data sets. The factor for modifying the gradient may be determined based on a ratio of the number of examples of the class with a fewest members to the number of examples of a present class. The gradient associated with the present class is modified based on the above determined factor.

公开(公告)号：US20150206048A1

公开(公告)日：2015-07-23

申请号：US14449101

申请日：2014-07-31

Applicant: QUALCOMM Incorporated

Inventor： Sachin Subhash TALATHI ,  David Jonathan JULIAN ,  Venkata Sreekanta Reddy ANNAPUREDDY

IPC: G06N3/04

CPC classification number: G06N3/08 ,  G06N3/0481 ,  G06N3/049 ,  G06N3/082

Abstract: A method for selecting a reduced number of model neurons in a neural network includes generating a first sparse set of non-zero decoding vectors. Each of the decoding vector is associated with a synapse between a first neuron layer and a second neuron layer. The method further includes implementing the neural network only with selected model neurons in the first neuron layer associated with the non-zero decoding vectors.

Abstract translation: 用于在神经网络中选择减少数量的模型神经元的方法包括生成非零解码矢量的第一稀疏集合。 每个解码矢量与第一神经元层和第二神经元层之间的突触相关联。 该方法还包括仅在与非零解码矢量相关联的第一神经元层中实施神经网络与选定的模型神经元。

公开(公告)号：US20140351186A1

公开(公告)日：2014-11-27

申请号：US14084302

申请日：2013-11-19

Applicant: QUALCOMM Incorporated

Inventor： David Jonathan JULIAN ,  Jeffrey Alexander LEVIN ,  Kristopher PETERSON ,  Ravindra Manohar PATWARDHAN

IPC: G06N3/08

CPC classification number: G06N3/08 ,  G06N3/049 ,  G06N3/10

Abstract: Methods and apparatus are provided for implementing spike-timing dependent plasticity (STDP) using windowing of spikes. One example method for operating an artificial nervous system generally includes recording spike times for a first artificial neuron, recording spike times for a second artificial neuron coupled to the first artificial neuron via a synapse, processing spikes for the second artificial neuron according to a window based at least in part on the spike times for the first artificial neuron, and updating a parameter (e.g., a weight or a delay) of the synapse based on the processing.

Abstract translation: 提供了使用尖峰窗口来实现尖峰时序相关可塑性（STDP）的方法和装置。 用于操作人造神经系统的一个示例性方法通常包括记录第一人造神经元的尖峰时间，通过突触记录耦合到第一人造神经元的第二人造神经元的尖峰时间，根据基于窗口的第二人造神经元的尖峰 至少部分地基于第一人造神经元的尖峰时间，以及基于该处理更新突触的参数（例如，重量或延迟）。

公开(公告)号：US20170169314A1

公开(公告)日：2017-06-15

申请号：US15247805

申请日：2016-08-25

Applicant: QUALCOMM Incorporated

Inventor： Daniel Hendricus Franciscus DIJKMAN ,  David Jonathan JULIAN

IPC: G06K9/66 ,  G06K9/62 ,  G06K9/46

CPC classification number: G06K9/66 ,  G06K9/3233 ,  G06K9/4628 ,  G06K9/623 ,  G06K9/6257 ,  G06K9/6261 ,  G06K9/627 ,  G06K9/628

Abstract: A method of training for image classification includes labelling a crop from an image including an object of interest. The crop may be labelled with an indication of whether the object of interest is framed, partially framed or not present in the crop. The method may also include assigning a fully framed class to the labelled crop, including the object of interest, if the object of interest is framed. A labelled crop may be assigned a partially framed class if the object of interest is partially framed. A background class may be assigned to a labelled crop if the object of interest is not present in the crop.

公开(公告)号：US20170032247A1

公开(公告)日：2017-02-02

申请号：US14859082

申请日：2015-09-18

Applicant: QUALCOMM Incorporated

Inventor： Henok Tefera TADESSE ,  Avijit CHAKRABORTY ,  David Jonathan JULIAN ,  Henricus Meinardus STOKMAN ,  Ork DE ROOIJ ,  Koen Erik Adriaan VAN DE SANDE ,  Venkata Sreekanta Reddy ANNAPUREDDY

IPC: G06N3/08 ,  G06N3/04 ,  G06N99/00

CPC classification number: G06N3/088 ,  G06K9/6265 ,  G06N3/02 ,  G06N3/04 ,  G06N20/00

Abstract: Multi-label classification is improved by determining thresholds and/or scale factors. Selecting thresholds for multi-label classification includes sorting a set of label scores associated with a first label to create an ordered list. Precision and recall values are calculated corresponding to a set of candidate thresholds from score values. The threshold is selected from the candidate thresholds for the first label based on target precision values or recall values. A scale factor is also selected for an activation function for multi-label classification where a metric of scores within a range is calculated. The scale factor is adjusted when the metric of scores are not within the range.

Abstract translation: 通过确定阈值和/或比例因子来提高多标签分类。 选择多标签分类的阈值包括对与第一标签相关联的一组标签分数进行排序以创建有序列表。 根据得分值对应于一组候选阈值计算精确度和回忆值。 基于目标精度值或召回值，从第一标签的候选阈值中选择阈值。 还为多标签分类的激活功能选择比例因子，其中计算范围内的分数的度量。 当分数的度量不在该范围内时，调整比例因子。

公开(公告)号：US20160267395A1

公开(公告)日：2016-09-15

申请号：US14856481

申请日：2015-09-16

Applicant: QUALCOMM Incorporated

Inventor： David Jonathan JULIAN ,  Anthony SARAH

IPC: G06N99/00 ,  G06N5/04

CPC classification number: G06N99/005 ,  G06K9/00107 ,  G06K9/6262 ,  G06K9/6269 ,  G06N3/02 ,  G06N5/046

Abstract: A method of online training of a classifier includes determining a distance from one or more feature vectors of an object to a first predetermined decision boundary established during off-line training for the classifier. The method also includes updating a decision rule as a function of the distance. The method further includes classifying a future example based on the updated decision rule.

Abstract translation: 分类器的在线训练的方法包括确定从物体的一个或多个特征向量到在分类器的离线训练期间建立的第一预定判定边界的距离。 该方法还包括根据距离更新决策规则。 该方法还包括基于更新的决策规则对未来示例进行分类。

公开(公告)号：US20160217369A1

公开(公告)日：2016-07-28

申请号：US14846579

申请日：2015-09-04

Applicant: QUALCOMM Incorporated

Inventor： Venkata Sreekanta Reddy ANNAPUREDDY ,  Daniel Hendricus Franciscus DIJKMAN ,  David Jonathan JULIAN

IPC: G06N3/08

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

Abstract: Compressing a machine learning network, such as a neural network, includes replacing one layer in the neural network with compressed layers to produce the compressed network. The compressed network may be fine-tuned by updating weight values in the compressed layer(s).

Abstract translation: 压缩诸如神经网络的机器学习网络包括用压缩层替换神经网络中的一层以产生压缩网络。 压缩网络可以通过更新压缩层中的权重值来进行微调。

公开(公告)号：US20150324688A1

公开(公告)日：2015-11-12

申请号：US14483054

申请日：2014-09-10

Applicant: QUALCOMM Incorporated

Inventor： Casimir Matthew WIERZYNSKI ,  David Jonathan JULIAN ,  Anthony SARAH

IPC: G06N3/08

CPC classification number: G06N3/049 ,  G06N3/0454 ,  G06N3/08

Abstract: A method of generating a classifier model includes distributing a common feature model to two or more users. Multiple classifiers are trained on top of the common feature model. The method further includes distributing a first classifier of the multiple classifiers to a first user and a second classifier of the multiple classifiers to a second user.

Abstract translation: 生成分类器模型的方法包括将公共特征模型分发给两个或更多个用户。 在通用特征模型之上训练多个分类器。 该方法还包括将多个分类器的第一分类器分配给第一用户，并将多个分类器的第二分类器分配给第二用户。

公开(公告)号：US20150324686A1

公开(公告)日：2015-11-12

申请号：US14464558

申请日：2014-08-20

Applicant: QUALCOMM Incorporated

Inventor： David Jonathan JULIAN ,  Anthony SARAH ,  Casimir Matthew WIERZYNSKI

IPC: G06N3/08

CPC classification number: G06N20/00 ,  G06N3/08

Abstract: A method of learning a model includes receiving model updates from one or more users. The method also includes computing an updated model based on a previous model and the model updates. The method further includes transmitting data related to a subset of the updated model to the a user(s) based on the updated model.

Abstract translation: 学习模型的方法包括从一个或多个用户接收模型更新。 该方法还包括基于先前的模型和模型更新来计算更新的模型。 所述方法还包括基于所更新的模型向所述用户发送与所述更新的模型的子集有关的数据。