Optimizing neural networks for generating analytical or predictive outputs

L Jordan, M Turner, M McBurnett - US Patent 11,049,019, 2021 - Google Patents
Certain embodiments involve generating or optimizing a neural network for generating
analytical or predictive outputs. The neural network can be generated using a relationship …

Block-diagonal hessian-free optimization for recurrent and convolutional neural networks

H Zhang, C Xiong - US Patent 11,386,327, 2022 - Google Patents
Embodiments for training a neural network are provided. A neural network is divided into a
first block and a second block, and the parameters in the first block and second block are …

Optimizing neural networks for risk assessment

M Turner, M McBurnett - US Patent 10,977,556, 2021 - Google Patents
Certain embodiments involve generating or optimizing a neural network for risk assessment.
The neural network can be generated using a relationship between various predictor …

Machine-learning techniques for monotonic neural networks

M Turner, L Jordan, A Joshua - US Patent 11,468,315, 2022 - Google Patents
In some aspects, a computing system can generate and optimize a neural network for risk
assessment. The neural network can be trained to enforce a monotonic relationship …

Optimizing automated modeling algorithms for risk assessment and generation of explanatory data

M Turner, M McBurnett, Y Zhang - US Patent 11,734,591, 2023 - Google Patents
Certain aspects involve optimizing neural networks or other models for assessing risks and
generating explanatory data regarding predictor variables used in the model. In one …

Optimizing neural networks for risk assessment

M Turner, M McBurnett - US Patent 10,963,791, 2021 - Google Patents
Certain embodiments involve generating or optimizing a neural network for risk assessment.
The neural network can be generated using a relationship between various predictor …

Action selection neural network training using imitation learning in latent space

SE Reed, Y Aytar, Z Wang, T Paine… - US Patent …, 2023 - Google Patents
2019-12-05 Assigned to DEEPMIND TECHNOLOGIES LIMITED reassignment DEEPMIND
TECHNOLOGIES LIMITED ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT …

Machine-learning techniques for monotonic neural networks

M Turner, L Jordan, A Joshua - US Patent 11,010,669, 2021 - Google Patents
In some aspects, a computing system can generate and optimize a neural network for risk
assessment. The neural network can be trained to enforce a monotonic relationship …

Optimizing automated modeling algorithms for risk assessment and generation of explanatory data

M Turner, M McBurnett, Y Zhang - US Patent 10,997,511, 2021 - Google Patents
Certain aspects involve optimizing neural networks or other models for assessing risks and
generating explanatory data regarding predictor variables used in the model. In one …

Optimizing automated modeling algorithms for risk assessment and generation of explanatory data

M Turner, M McBurnett, Y Zhang - US Patent 11,238,355, 2022 - Google Patents
Certain aspects involve optimizing neural networks or other models for assessing risks and
generating explanatory data regarding predictor variables used in the model. In one …