Patents by Inventor Oluwatobi Olabiyi

Oluwatobi Olabiyi 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).

  • Publication number: 20210327428
    Abstract: Systems and methods for generating responses to user input such as dialogues, and images are discussed. The system may generate, by a response generation module of at least one server, an optimal generated response to the user communication by applying an generative adversarial network. In some embodiments, the generative adversarial network may include a hierarchical recurrent encoder decoder generative adversarial network including a generator and a discriminator component.
    Type: Application
    Filed: June 28, 2021
    Publication date: October 21, 2021
    Applicant: Capital One Services, LLC
    Inventors: Oluwatobi OLABIYI, Erik T. Mueller
  • Patent number: 11120353
    Abstract: By way of example, the technology disclosed by this document may be implemented in a method that includes receiving stored sensor data describing characteristics of a vehicle in motion at a past time and extracting features for prediction and features for recognition from the stored sensor data. The features for prediction may be input into a prediction network, which may generate a predicted label for a past driver action based on the features for prediction. The features for recognition may be input into a recognition network, which may generate a recognized label for the past driver action based on the features for recognition. In some instances, the method may include training prediction network weights of the prediction network using the recognized label and the predicted label.
    Type: Grant
    Filed: November 28, 2016
    Date of Patent: September 14, 2021
    Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
    Inventors: Oluwatobi Olabiyi, Eric Martinson
  • Publication number: 20210233519
    Abstract: Various embodiments may be generally directed to the use of an adversarial learning framework for persona-based dialogue modeling. In some embodiments, automated multi-turn dialogue response generation may be performed using a persona-based hierarchical recurrent encoder-decoder-based generative adversarial network (phredGAN). Such a phredGAN may feature a persona-based hierarchical recurrent encoder-decoder (PHRED) generator and a conditional discriminator. In some embodiments, the conditional discriminator may include an adversarial discriminator that is provided with attribute representations as inputs. In some other embodiments, the conditional discriminator may include an attribute discriminator, and attribute representations may be handled as targets of the attribute discriminator. The embodiments are not limited in this context.
    Type: Application
    Filed: April 12, 2021
    Publication date: July 29, 2021
    Applicant: Capital One Services, LLC
    Inventors: Oluwatobi OLABIYI, Alan SALIMOV, Anish KHAZANE, Erik MUELLER
  • Publication number: 20210232925
    Abstract: Aspects described herein may allow for the application of stochastic gradient boosting techniques to the training of deep neural networks by disallowing gradient back propagation from examples that are correctly classified by the neural network model while still keeping correctly classified examples in the gradient averaging. Removing the gradient contribution from correctly classified examples may regularize the deep neural network and prevent the model from overfitting. Further aspects described herein may provide for scheduled boosting during the training of the deep neural network model conditioned on a mini-batch accuracy and/or a number of training iterations. The model training process may start un-boosted, using maximum likelihood objectives or another first loss function.
    Type: Application
    Filed: April 16, 2021
    Publication date: July 29, 2021
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller, Christopher Larson
  • Patent number: 11049500
    Abstract: Systems and methods for generating responses to user input such as dialogues, and images are discussed. The system may generate, by a response generation module of at least one server, an optimal generated response to the user communication by applying an generative adversarial network. In some embodiments, the generative adversarial network may include a hierarchical recurrent encoder decoder generative adversarial network including a generator and a discriminator component.
    Type: Grant
    Filed: August 29, 2019
    Date of Patent: June 29, 2021
    Assignee: Capital One Services, LLC
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller
  • Patent number: 10990878
    Abstract: Aspects described herein may allow for the application of stochastic gradient boosting techniques to the training of deep neural networks by disallowing gradient back propagation from examples that are correctly classified by the neural network model while still keeping correctly classified examples in the gradient averaging. Removing the gradient contribution from correctly classified examples may regularize the deep neural network and prevent the model from overfitting. Further aspects described herein may provide for scheduled boosting during the training of the deep neural network model conditioned on a mini-batch accuracy and/or a number of training iterations. The model training process may start un-boosted, using maximum likelihood objectives or another first loss function.
    Type: Grant
    Filed: March 5, 2019
    Date of Patent: April 27, 2021
    Assignee: Capital One Services, LLC
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller, Christopher Larson
  • Patent number: 10978051
    Abstract: Various embodiments may be generally directed to the use of an adversarial learning framework for persona-based dialogue modeling. In some embodiments, automated multi-turn dialogue response generation may be performed using a persona-based hierarchical recurrent encoder-decoder-based generative adversarial network (phredGAN). Such a phredGAN may feature a persona-based hierarchical recurrent encoder-decoder (PHRED) generator and a conditional discriminator. In some embodiments, the conditional discriminator may include an adversarial discriminator that is provided with attribute representations as inputs. In some other embodiments, the conditional discriminator may include an attribute discriminator, and attribute representations may be handled as targets of the attribute discriminator. The embodiments are not limited in this context.
    Type: Grant
    Filed: September 4, 2019
    Date of Patent: April 13, 2021
    Assignee: CAPITAL ONE SERVICES, LLC
    Inventors: Oluwatobi Olabiyi, Alan Salimov, Anish Khazane, Erik Mueller
  • Publication number: 20210027023
    Abstract: Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in the dialogue data better than the existing recurrent neural network-based architectures. Additionally, machine classifiers may model the joint distribution of the context and response as opposed to the conditional distribution of the response given the context as employed in sequence-to-sequence frameworks. Further, input data may be bidirectionally encoded using both forward and backward separators. The forward and backward representations of the input data may be used to train the machine classifiers using a single generative model and/or shared parameters between the encoder and decoder of the machine classifier. During inference, the backward model may be used to reevaluate previously generated output sequences and the forward model may be used to generate an output sequence based on the previously generated output sequences.
    Type: Application
    Filed: July 22, 2020
    Publication date: January 28, 2021
    Inventors: Oluwatobi Olabiyi, Zachary Kulis, Erik T. Mueller
  • Publication number: 20210027025
    Abstract: Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in particular tasks, such as turn-based dialogues. Machine classifiers may be used to help users to perform tasks indicated by the user. When a user utterance is received, natural language processing techniques may be used to understand the user's intent. Templates may be determined based on the user's intent in the generation of responses to solicit information from the user. A variety of persona attributes may be determined for a user. The persona attributes may be determined based on the user's utterances and/or provided as metadata included with the user's utterances. A response persona may be used to generate responses to the user's utterances such that the generated responses match a tone appropriate to the task. A response persona may be used to generate templates to solicit additional information and/or generate responses appropriate to the task.
    Type: Application
    Filed: July 22, 2020
    Publication date: January 28, 2021
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller, Diana Mingels, Zachary Kulis
  • Publication number: 20210027770
    Abstract: Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in particular tasks, such as turn-based dialogues. Machine classifiers may be used to help users to perform tasks indicated by the user. When a user utterance is received, natural language processing techniques may be used to understand the user's intent. Templates may be determined based on the user's intent in the generation of responses to solicit information from the user. A variety of persona attributes may be determined for a user. The persona attributes may be determined based on the user's utterances and/or provided as metadata included with the user's utterances. A response persona may be used to generate responses to the user's utterances such that the generated responses match a tone appropriate to the task. A response persona may be used to generate templates to solicit additional information and/or generate responses appropriate to the task.
    Type: Application
    Filed: July 22, 2020
    Publication date: January 28, 2021
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller, Rui Zhang, Zachary Kulis, Varun Singh
  • Publication number: 20210027022
    Abstract: Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in the dialogue data better than the existing RNN-based architectures. Additionally, machine classifiers may model the joint distribution of the context and response as opposed to the conditional distribution of the response given the context as employed in sequence-to-sequence frameworks. Machine classifiers in accordance with embodiments further append random paddings before and/or after the input data to reduce the syntactic redundancy in the input data, thereby improving the performance of the machine classifiers for a variety of dialogue-related tasks. The random padding of the input data may further provide regularization during the training of the machine classifier and/or reduce exposure bias. In a variety of embodiments, the input data may be encoded based on subword tokenization.
    Type: Application
    Filed: July 22, 2020
    Publication date: January 28, 2021
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller, Rui Zhang
  • Publication number: 20200372898
    Abstract: Systems described herein may use machine classifiers to perform a variety of natural language understanding tasks including, but not limited to multi-turn dialogue generation. Machine classifiers in accordance with aspects of the disclosure may model multi-turn dialogue as a one-to-many prediction task. The machine classifier may be trained using adversarial bootstrapping between a generator and a discriminator with multi-turn capabilities. The machine classifiers may be trained in both auto-regressive and traditional teacher-forcing modes, with the maximum likelihood loss of the auto-regressive outputs being weighted by the score from a metric-based discriminator model. The discriminators input may include a mixture of ground truth labels, the teacher-forcing outputs of the generator, and/or negative examples from the dataset. This mixture of input may allow for richer feedback on the autoregressive outputs of the generator.
    Type: Application
    Filed: May 21, 2020
    Publication date: November 26, 2020
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller
  • Publication number: 20200265321
    Abstract: Aspects discussed herein may relate to methods and techniques for embedding constrained and unconstrained optimization programs as layers in a neural network architecture. Systems are provided that implement a method of solving a particular optimization problem by a neural network architecture. Prior systems required use of external software to pre-solve optimization programs so that previously determined parameters could be used as fixed input in the neural network architecture. Aspects described herein may transform the structure of common optimization problems/programs into forms suitable for use in a neural network. This transformation may be invertible, allowing the system to learn the solution to the optimization program using gradient descent techniques via backpropagation of errors through the neural network architecture. Thus these optimization layers may be solved via operation of the neural network itself.
    Type: Application
    Filed: February 14, 2020
    Publication date: August 20, 2020
    Inventors: Tarek Aziz Lahlou, Christopher Larson, Oluwatobi Olabiyi
  • Publication number: 20200265296
    Abstract: Aspects described herein may allow for the application of stochastic gradient boosting techniques to the training of deep neural networks by disallowing gradient back propagation from examples that are correctly classified by the neural network model while still keeping correctly classified examples in the gradient averaging. Removing the gradient contribution from correctly classified examples may regularize the deep neural network and prevent the model from overfitting. Further aspects described herein may provide for scheduled boosting during the training of the deep neural network model conditioned on a mini-batch accuracy and/or a number of training iterations. The model training process may start un-boosted, using maximum likelihood objectives or another first loss function.
    Type: Application
    Filed: March 5, 2019
    Publication date: August 20, 2020
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller, Christopher Larson
  • Patent number: 10611379
    Abstract: By way of example, the technology disclosed by this document is capable of receiving signal data from one or more sensors; inputting the signal data into an input layer of a deep neural network (DNN), the DNN including one or more layers; generating, using the one or more layers of the DNN, one or more spatial representations of the signal data; generating, using one or more hierarchical temporal memories (HTMs) respectively associated with the one or more layers of the DNNs, one or more temporal predictions by the DNN based on the one or more spatial representations; and generating an anticipation of a future outcome by recognizing a temporal pattern based on the one or more temporal predictions.
    Type: Grant
    Filed: August 16, 2016
    Date of Patent: April 7, 2020
    Assignee: Toyota Jidosha Kabushiki Kaisha
    Inventors: Oluwatobi Olabiyi, Veeraganesh Yalla, Eric Martinson
  • Publication number: 20200098353
    Abstract: Various embodiments may be generally directed to the use of an adversarial learning framework for persona-based dialogue modeling. In some embodiments, automated multi-turn dialogue response generation may be performed using a persona-based hierarchical recurrent encoder-decoder-based generative adversarial network (phredGAN). Such a phredGAN may feature a persona-based hierarchical recurrent encoder-decoder (PHRED) generator and a conditional discriminator. In some embodiments, the conditional discriminator may include an adversarial discriminator that is provided with attribute representations as inputs. In some other embodiments, the conditional discriminator may include an attribute discriminator, and attribute representations may be handled as targets of the attribute discriminator. The embodiments are not limited in this context.
    Type: Application
    Filed: September 4, 2019
    Publication date: March 26, 2020
    Applicant: Capital One Services, LLC
    Inventors: Oluwatobi OLABIYI, Alan SALIMOV, Anish KHAZANE, Erik MUELLER
  • Publication number: 20190385609
    Abstract: Systems and methods for generating responses to user input such as dialogues, and images are discussed. The system may generate, by a response generation module of at least one server, an optimal generated response to the user communication by applying an generative adversarial network. In some embodiments, the generative adversarial network may include a hierarchical recurrent encoder decoder generative adversarial network including a generator and a discriminator component.
    Type: Application
    Filed: August 29, 2019
    Publication date: December 19, 2019
    Applicant: Capital One Services,LLC
    Inventors: Oluwatobi OLABIYI, Erik T. Mueller
  • Patent number: 10510002
    Abstract: Aspects described herein may allow for the application of stochastic gradient boosting techniques to the training of deep neural networks by disallowing gradient back propagation from examples that are correctly classified by the neural network model while still keeping correctly classified examples in the gradient averaging. Removing the gradient contribution from correctly classified examples may regularize the deep neural network and prevent the model from overfitting. Further aspects described herein may provide for scheduled boosting during the training of the deep neural network model conditioned on a mini-batch accuracy and/or a number of training iterations. The model training process may start un-boosted, using maximum likelihood objectives or another first loss function.
    Type: Grant
    Filed: February 14, 2019
    Date of Patent: December 17, 2019
    Assignee: Capital One Services, LLC
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller, Christopher Larson
  • Patent number: 10510003
    Abstract: Aspects described herein may allow for the application of stochastic gradient boosting techniques to the training of deep neural networks by disallowing gradient back propagation from examples that are correctly classified by the neural network model while still keeping correctly classified examples in the gradient averaging. Removing the gradient contribution from correctly classified examples may regularize the deep neural network and prevent the model from overfitting. Further aspects described herein may provide for scheduled boosting during the training of the deep neural network model conditioned on a mini-batch accuracy and/or a number of training iterations. The model training process may start un-boosted, using maximum likelihood objectives or another first loss function.
    Type: Grant
    Filed: March 5, 2019
    Date of Patent: December 17, 2019
    Assignee: Capital One Services, LLC
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller, Christopher Larson
  • Patent number: 10403284
    Abstract: Systems and methods for generating responses to user input such as dialogs, and images are discussed. The system may generate, by a response generation module of at least one server, an optimal generated response to the user communication by applying an generative adversarial network. In some embodiments, the generative adversarial network may include a hierarchical recurrent encoder decoder generative adversarial network including a generator and a discriminator component.
    Type: Grant
    Filed: November 5, 2018
    Date of Patent: September 3, 2019
    Assignee: Capital Services, LLC
    Inventors: Oluwatobi Olabiyi, Erik T. Mueller