-
公开(公告)号：US20210216813A1
公开(公告)日：2021-07-15
申请号：US16743306
申请日：2020-01-15
发明人： Maziyar Baran Pouyan , Yao A. Yang , Saeideh Shahrokh Esfahani , Andrew E. Fano , David William Vinson , Timothy M. Shea , Jesus Sanchez-Macias
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for clustering data are disclosed. In one aspect, a method includes the actions of receiving feature vectors. The actions further include, for a subset of the feature vectors, accessing a first label. The actions further include generating a classifier that is configured to associate a given feature vector with a feature vector of the subset of the feature vectors. The actions further include applying the feature vectors that are not included in the subset of the feature vectors to the classifier. The actions further include generating a dissimilarity matrix. The actions further include, based on the dissimilarity matrix, generating a graph. The actions further include, for each node of the graph, determining a second label. The actions further include, based on the second labels and the first labels, determining a training label for each feature vector.
-
公开(公告)号：US20240096313A1
公开(公告)日：2024-03-21
申请号：US17946523
申请日：2022-09-16
发明人： Lavinia Andreea Danielescu , Timothy M. Shea , Kenneth Michael Stewart , Noah Gideon Pacik-Nelson , Eric Michael Gallo
CPC分类号： G10L15/16 , G10L15/063 , G10L15/197 , G10L15/22 , G10L15/30 , G10L25/21 , G10L2015/0635 , G10L2015/223
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for recognizing speech using a spiking neural network acoustic model implemented on a neuromorphic processor are described. In one aspect, a method includes receiving, a trained acoustic model implemented as a spiking neural network (SNN) on a neuromorphic processor of a client device, a set of feature coefficients that represent acoustic energy of input audio received from a microphone communicably coupled to the client device. The acoustic model is trained to predict speech sounds based on input feature coefficients. The acoustic model generates output data indicating predicted speech sounds corresponding to the set of feature coefficients that represent the input audio received from the microphone. The neuromorphic processor updates one or more parameters of the acoustic model using one or more learning rules and the predicted speech sounds of the output data.
-
公开(公告)号：US11544491B2
公开(公告)日：2023-01-03
申请号：US16743306
申请日：2020-01-15
发明人： Maziyar Baran Pouyan , Yao A. Yang , Saeideh Shahrokh Esfahani , Andrew E. Fano , David William Vinson , Timothy M. Shea , Jesus Sanchez-Macias
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for clustering data are disclosed. In one aspect, a method includes the actions of receiving feature vectors. The actions further include, for a subset of the feature vectors, accessing a first label. The actions further include generating a classifier that is configured to associate a given feature vector with a feature vector of the subset of the feature vectors. The actions further include applying the feature vectors that are not included in the subset of the feature vectors to the classifier. The actions further include generating a dissimilarity matrix. The actions further include, based on the dissimilarity matrix, generating a graph. The actions further include, for each node of the graph, determining a second label. The actions further include, based on the second labels and the first labels, determining a training label for each feature vector.
-
公开(公告)号：US20210224584A1
公开(公告)日：2021-07-22
申请号：US16744506
申请日：2020-01-16
发明人： Maziyar Baran Pouyan , Yao A. Yang , Saeideh Shahrokh Esfahani , Andrew E. Fano , David William Vinson , Timothy M. Shea
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for clustering data are disclosed. In one aspect, a method includes the actions of receiving feature vectors. The actions further include accessing rules that each relate one or more values of the feature vectors to a respective label of a plurality of labels. The actions further include, based on the rules, generating heuristics that each identify related values of the feature vectors. The actions further include, for each of the heuristics, generating a matrix that reflects a similarity of the feature vectors. The actions further include, based on the matrices that each reflects a respective similarity of the feature vectors, generating clusters that each include a subset of the feature vectors. The actions further include, for each cluster, determining a label of the plurality of labels.
-
公开(公告)号：US20240169696A1
公开(公告)日：2024-05-23
申请号：US17992205
申请日：2022-11-22
IPC分类号： G06V10/774 , G06V10/762 , G06V10/764 , G06V10/776 , G06V10/82 , G06V40/20
CPC分类号： G06V10/774 , G06V10/762 , G06V10/764 , G06V10/776 , G06V10/82 , G06V40/20
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for updating a trained gesture recognition model deployed on a neuromorphic processor that has been trained to process data that characterizes the new gesture and to determine a gesture classification for the gesture are described. A method includes receiving data that characterizes a new gesture and processing the data to generate a new embedding in a latent space. For each of multiple clusters of reference embeddings in the latent space, a respective distance in the latent space between the cluster of reference embedding and the new embedding is determined. A determination is made, based on applying one or more learning rules to the distances, one or more procedures to update the gesture recognition model. A determination is made, in accordance with the determined procedure(s), an update to values of one or more parameters of the gesture recognition model.
-
公开(公告)号：US20230290340A1
公开(公告)日：2023-09-14
申请号：US18118619
申请日：2023-03-07
发明人： Lavinia Andreea Danielescu , Kenneth Michael Stewart , Noah Gideon Pacik-Nelson , Timothy M. Shea
IPC分类号： G10L15/16 , G10L21/013 , G10L25/24
CPC分类号： G10L15/16 , G10L21/013 , G10L25/24
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for converting audio to spikes for input to a spiking neural network configured to recognize speech based on the spikes are described. In some aspects, a method includes obtaining audio data and generating frequency domain audio signals that represent the audio data by converting the audio data into a frequency domain. The frequency domain audio signals are mapped into a set of Mel-frequency bands to obtain Mel-scale frequency audio signals. A log transformation is performed on the Mel-scale frequency audio signals to obtain log-Mel signals. Spike input is generated for input to a spiking neural network (SNN) model by converting the log-Mel signals to the series of spikes. The spike input is provided as an input to the SNN model.
-
公开(公告)号：US11625621B2
公开(公告)日：2023-04-11
申请号：US16744506
申请日：2020-01-16
发明人： Maziyar Baran Pouyan , Yao A. Yang , Saeideh Shahrokh Esfahani , Andrew E. Fano , David William Vinson , Timothy M. Shea
IPC分类号： G06N5/025 , G06N20/10 , G06F18/2323 , G06F18/214 , G06F18/2411 , G06N5/01
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for clustering data are disclosed. In one aspect, a method includes the actions of receiving feature vectors. The actions further include accessing rules that each relate one or more values of the feature vectors to a respective label of a plurality of labels. The actions further include, based on the rules, generating heuristics that each identify related values of the feature vectors. The actions further include, for each of the heuristics, generating a matrix that reflects a similarity of the feature vectors. The actions further include, based on the matrices that each reflects a respective similarity of the feature vectors, generating clusters that each include a subset of the feature vectors. The actions further include, for each cluster, determining a label of the plurality of labels.
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.016 秒)
