Patents by Inventor Ryan Rifkin

Ryan Rifkin has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10285005
    Abstract: There is disclosed herein a non-volatile machine-readable medium storing a program, a system and method for enabling proximity-based, peer-to-peer sharing of media in which a first device having a wireless communication surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices and a list of the authenticated connections is maintained. Without input from a user, media is shared between the individual devices on the authenticated connections list and a remote server, subject to permissions pre-set by the individual devices. Devices not included in the list of authenticated connections are blocked from accessing the media. Access to the media is available for a period of time, after which time access to the media is blocked for all devices.
    Type: Grant
    Filed: November 13, 2018
    Date of Patent: May 7, 2019
    Assignee: Aircam Inc.
    Inventors: Ryan Rifkin, Evan Rifkin, Steve Lackenby, Alex Pronin, David Hopkins
  • Patent number: 10285004
    Abstract: There is disclosed herein a system and method for enabling access to media. The method includes receiving media and a media location indicating a location from which the media was shared, storing the media in conjunction with a geofence area defined by the media location plus a pre-determined area around the media location, receiving a request for any media from a device along with a device location indicating a location of the device making the request, and comparing the device location with the geofence area and, when the device location is within the geofence area, providing access to the media, and when the device location is outside of the geofence area, denying access to the media.
    Type: Grant
    Filed: March 20, 2018
    Date of Patent: May 7, 2019
    Inventors: Evan Rifkin, David Hopkins, Ryan Rifkin
  • Publication number: 20190082293
    Abstract: There is disclosed herein a non-volatile machine-readable medium storing a program, a system and method for enabling proximity-based, peer-to-peer sharing of media in which a first device having a wireless communication surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices and a list of the authenticated connections is maintained. Without input from a user, media is shared between the individual devices on the authenticated connections list and a remote server, subject to permissions pre-set by the individual devices. Devices not included in the list of authenticated connections are blocked from accessing the media. Access to the media is available for a period of time, after which time access to the media is blocked for all devices.
    Type: Application
    Filed: November 13, 2018
    Publication date: March 14, 2019
    Inventors: Ryan RIFKIN, Evan RIFKIN, Steve Lackenby, Alex Pronin, David Hopkins
  • Publication number: 20190082290
    Abstract: There is disclosed herein a system and method for enabling access to media. The method includes receiving media and a media location indicating a location from which the media was shared, storing the media in conjunction with a geofence area defined by the media location plus a pre-determined area around the media location, receiving a request for any media from a device along with a device location indicating a location of the device making the request, and comparing the device location with the geofence area and, when the device location is within the geofence area, providing access to the media, and when the device location is outside of the geofence area, denying access to the media.
    Type: Application
    Filed: March 20, 2018
    Publication date: March 14, 2019
    Inventors: Evan Rifkin, David Hopkins, Ryan Rifkin
  • Patent number: 10154374
    Abstract: There is disclosed herein a system and method for enabling proximity-based, peer-to-peer sharing of media in which a first device having a wireless communication surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices and a list of the connections is maintained. Without input from a user, media is shared between the individual devices on the connections list and between the individual devices on the connections list and a remote server. Devices not included in the list of connections are blocked from accessing the media. Access to the media is available for a pre-determined period of time, after which time access to the media is blocked for all devices.
    Type: Grant
    Filed: June 12, 2018
    Date of Patent: December 11, 2018
    Assignee: Aircam Inc.
    Inventors: Ryan Rifkin, Evan Rifkin, Steve Lackenby, Alex Pronin, David Hopkins
  • Publication number: 20180302745
    Abstract: There is disclosed herein a system and method for enabling proximity-based, peer-to-peer sharing of media in which a first device having a wireless communication surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices and a list of the connections is maintained. Without input from a user, media is shared between the individual devices on the connections list and between the individual devices on the connections list and a remote server. Devices not included in the list of connections are blocked from accessing the media. Access to the media is available for a pre-determined period of time, after which time access to the media is blocked for all devices.
    Type: Application
    Filed: June 12, 2018
    Publication date: October 18, 2018
    Inventors: Ryan RIFKIN, Evan RIFKIN, Steve Lackenby, Alex Pronin, David Hopkins
  • Patent number: 10091317
    Abstract: A method and apparatus for proximity-based content sharing on wireless devices is presented in which a first device having a wireless communication region surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices. In response to a user action data is pushed from the wireless device to other wireless devices in the region. Communication connections can also be formed between devices in the region and devices outside the region and data may be pushed to the devices outside the region. Users can block other devices either within the region or outside the region so that they do not receive pushed data.
    Type: Grant
    Filed: March 14, 2016
    Date of Patent: October 2, 2018
    Assignee: Aircam Inc.
    Inventors: Evan Rifkin, Ryan Rifkin, Alex Pronin, Steve Lackenby
  • Publication number: 20180197533
    Abstract: The various implementations described herein include methods, devices, and systems for recognizing speech, such as user commands. In one aspect, a method includes: (1) receiving audio input data via the one or more microphones; (2) generating a plurality of energy channels for the audio input data; (3) generating a feature vector by performing a per-channel normalization to each channel of the plurality of energy channels; and (4) obtaining recognized speech from the audio input utilizing the feature vector.
    Type: Application
    Filed: December 12, 2017
    Publication date: July 12, 2018
    Inventors: Richard Lyon, Christopher Hughes, Yuxuan Wang, Ryan Rifkin, Pascal Getreuer
  • Patent number: 9961493
    Abstract: There is disclosed herein a system and method for enabling access to media. The method includes receiving media and a media location indicating a location from which the media was shared, storing the media in conjunction with a geofence area defined by the media location plus a pre-determined area around the media location, receiving a request for any media from a device along with a device location indicating a location of the device making the request, and comparing the device location with the geofence area and, when the device location is within the geofence area, providing access to the media, and when the device location is outside of the geofence area, denying access to the media.
    Type: Grant
    Filed: September 8, 2017
    Date of Patent: May 1, 2018
    Assignee: Aircam Inc.
    Inventors: Evan Rifkin, David Hopkins, Ryan Rifkin
  • Publication number: 20170013076
    Abstract: A method and apparatus for proximity-based content sharing on wireless devices is presented in which a first device having a wireless communication region surrounding the device detects other wireless devices within the region. Communication connections are formed between the wireless devices. In response to a user action data is pushed from the wireless device to other wireless devices in the region. Communication connections can also be formed between devices in the region and devices outside the region and data may be pushed to the devices outside the region. Users can block other devices either within the region or outside the region so that they do not receive pushed data.
    Type: Application
    Filed: March 14, 2016
    Publication date: January 12, 2017
    Inventors: Ryan Rifkin, Evan Rifkin, Steve Lackenby, Alex Pronin
  • Patent number: 7853539
    Abstract: Sound discrimination techniques are disclosed that can be employed, for example, in the task of discriminating speech and non-speech in a noisy environment and other noise classification applications. In one particular embodiment, a classifier system is provided that includes a linear Regularized Least Squares classifier used directly on a high-dimensional cortical representation of the target sound. The regularization constant lambda (?) can be selected automatically, yielding a parameter-free learning system. In addition, the high-dimensional hyperplane can be viewed directly in the cortical space, leading to greater interpretability of the classifier results.
    Type: Grant
    Filed: November 14, 2006
    Date of Patent: December 14, 2010
    Assignee: Honda Motor Co., Ltd.
    Inventor: Ryan Rifkin
  • Patent number: 7685080
    Abstract: Techniques are disclosed that implement algorithms for rapidly finding the leave-one-out (LOO) error for regularized least squares (RLS) problems over a large number of values of the regularization parameter ?. Algorithms implementing the techniques use approximately the same time and space as training a single regularized least squares classifier/regression algorithm. The techniques include a classification/regression process suitable for moderate sized datasets, based on an eigendecomposition of the unregularized kernel matrix. This process is applied to a number of benchmark datasets, to show empirically that accurate classification/regression can be performed using a Gaussian kernel with surprisingly large values of the bandwidth parameter ?. It is further demonstrated how to exploit this large ? regime to obtain a linear-time algorithm, suitable for large datasets, that computes LOO values and sweeps over ?.
    Type: Grant
    Filed: September 27, 2006
    Date of Patent: March 23, 2010
    Assignee: Honda Motor Co., Ltd.
    Inventors: Ryan Rifkin, Ross Lippert
  • Patent number: 7475013
    Abstract: A system and method for voice recognition is disclosed. The system enrolls speakers using an enrollment voice samples and identification information. An extraction module characterizes enrollment voice samples with high-dimensional feature vectors or speaker data points. A data structuring module organizes data points into a high-dimensional data structure, such as a kd-tree, in which similarity between data points dictates a distance, such as a Euclidean distance, a Minkowski distance, or a Manhattan distance. The system recognizes a speaker using an unidentified voice sample. A data querying module searches the data structure to generate a subset of approximate nearest neighbors based on an extracted high-dimensional feature vector. A data modeling module uses Parzen windows to estimate a probability density function representing how closely characteristics of the unidentified speaker match enrolled speakers, in real-time, without extensive training data or parametric assumptions about data distribution.
    Type: Grant
    Filed: March 26, 2004
    Date of Patent: January 6, 2009
    Assignee: Honda Motor Co., Ltd.
    Inventor: Ryan Rifkin
  • Patent number: 7412425
    Abstract: A local-neighborhood Laplacian Eigenmap (LNLE) algorithm is provided for methods and systems for semi-supervised learning on manifolds of data points in a high-dimensional space. In one embodiment, an LNLE based method includes building an adjacency graph over a dataset of labelled and unlabelled points. The adjacency graph is then used for finding a set of local neighbors with respect to an unlabelled data point to be classified. An eigen decomposition of the local subgraph provides a smooth function over the subgraph. The smooth function can be evaluated and based on the function evaluation the unclassified data point can be labelled. In one embodiment, a transductive inference (TI) algorithmic approach is provided. In another embodiment, a semi-supervised inductive inference (SSII) algorithmic approach is provided for classification of subsequent data points. A confidence determination can be provided based on a number of labeled data points within the local neighborhood.
    Type: Grant
    Filed: April 14, 2005
    Date of Patent: August 12, 2008
    Assignee: Honda Motor Co., Ltd.
    Inventors: Ryan Rifkin, Stuart Andrews
  • Publication number: 20070094180
    Abstract: Techniques are disclosed that implement algorithms for rapidly finding the leave-one-out (LOO) error for regularized least squares (RLS) problems over a large number of values of the regularization parameter ?. Algorithms implementing the techniques use approximately the same time and space as training a single regularized least squares classifier/regression algorithm. The techniques include a classification/regression process suitable for moderate sized datasets, based on an eigendecomposition of the unregularized kernel matrix. This process is applied to a number of benchmark datasets, to show empirically that accurate classification/regression can be performed using a Gaussian kernel with surprisingly large values of the bandwidth parameter ?. It is further demonstrated how to exploit this large ? regime to obtain a linear-time algorithm, suitable for large datasets, that computes LOO values and sweeps over ?.
    Type: Application
    Filed: September 27, 2006
    Publication date: April 26, 2007
    Inventors: Ryan Rifkin, Ross Lippert
  • Publication number: 20070073538
    Abstract: Sound discrimination techniques are disclosed that can be employed, for example, in the task of discriminating speech and non-speech in a noisy environment and other noise classification applications. In one particular embodiment, a classifier system is provided that includes a linear Regularized Least Squares classifier used directly on a high-dimensional cortical representation of the target sound. The regularization constant lambda (?) can be selected automatically, yielding a parameter-free learning system. In addition, the high-dimensional hyperplane can be viewed directly in the cortical space, leading to greater interpretability of the classifier results.
    Type: Application
    Filed: November 14, 2006
    Publication date: March 29, 2007
    Inventor: Ryan Rifkin
  • Publication number: 20060235812
    Abstract: A local-neighborhood Laplacian Eigenmap (LNLE) algorithm is provided for methods and systems for semi-supervised learning on manifolds of data points in a high-dimensional space. In one embodiment, an LNLE based method includes building an adjacency graph over a dataset of labelled and unlabelled points. The adjacency graph is then used for finding a set of local neighbors with respect to an unlabelled data point to be classified. An eigen decomposition of the local subgraph provides a smooth function over the subgraph. The smooth function can be evaluated and based on the function evaluation the unclassified data point can be labelled. In one embodiment, a transductive inference (TI) algorithmic approach is provided. In another embodiment, a semi-supervised inductive inference (SSII) algorithmic approach is provided for classification of subsequent data points. A confidence determination can be provided based on a number of labeled data points within the local neighborhood.
    Type: Application
    Filed: April 14, 2005
    Publication date: October 19, 2006
    Applicant: HONDA MOTOR CO., LTD.
    Inventors: Ryan Rifkin, Stuart Andrews
  • Publication number: 20040225498
    Abstract: A system and method for voice recognition is disclosed. The system enrolls speakers using an enrollment voice samples and identification information. An extraction module characterizes enrollment voice samples with high-dimensional feature vectors or speaker data points. A data structuring module organizes data points into a high-dimensional data structure, such as a kd-tree, in which similarity between data points dictates a distance, such as a Euclidean distance, a Minkowski distance, or a Manhattan distance. The system recognizes a speaker using an unidentified voice sample. A data querying module searches the data structure to generate a subset of approximate nearest neighbors based on an extracted high-dimensional feature vector. A data modeling module uses Parzen windows to estimate a probability density function representing how closely characteristics of the unidentified speaker match enrolled speakers, in real-time, without extensive training data or parametric assumptions about data distribution.
    Type: Application
    Filed: March 26, 2004
    Publication date: November 11, 2004
    Inventor: Ryan Rifkin
  • Publication number: 20030225526
    Abstract: Methods are provided for the clssification of disease types (e.g., cancer types), outcome predictions, and treatment classes based on algorithmic classifiers used to analyze large datasets.
    Type: Application
    Filed: November 14, 2002
    Publication date: December 4, 2003
    Inventors: Todd R. Golub, Sayan Mukherjee, Sridhar Ramaswamy, Ryan Rifkin, Pablo Tamayo