Method for training a generative adversarial network (GAN), generative adversarial network, computer program, machine-readable memory medium, and device
D Terjek - US Patent 11,651,205, 2023 - Google Patents
Generative adversarial networks (GANs) are methods of unsupervised machine learning.
GANs include two artificial neuronal networks: a generator and a discriminator. The input …
GANs include two artificial neuronal networks: a generator and a discriminator. The input …
Gated attention neural networks
A system including an attention neural network that is configured to receive an input
sequence and to process the input sequence to generate an output is described. The …
sequence and to process the input sequence to generate an output is described. The …
Learning device, learning method, and computer-readable recording medium
S Harada - US Patent App. 16/696,514, 2020 - Google Patents
A learning device includes: a memory; and a processor coupled to the memory and
configured to: generate plural first subsets of time-series data by dividing time-series data …
configured to: generate plural first subsets of time-series data by dividing time-series data …
Reinforcement learning techniques for selecting a software policy network and autonomously controlling a corresponding software client based on selected policy …
V Carbune, T Deselaers - US Patent 11,651,196, 2023 - Google Patents
An automated assistant receives input from the user including spoken natural language
input (ie, utterances) and may respond by performing an action, by controlling another …
input (ie, utterances) and may respond by performing an action, by controlling another …
Systems and methods of autonomous voltage control in electric power systems
Abstract Systems and methods for autonomous voltage control in an electric power system
are disclosed which include acquiring state information at buses of the electric power …
are disclosed which include acquiring state information at buses of the electric power …
Training action selection neural networks using apprenticeship
An off-policy reinforcement learning actor-critic neural network system configured to select
actions from a continuous action space to be performed by an agent interacting with an …
actions from a continuous action space to be performed by an agent interacting with an …
True Positive Transplant
IPM Bataller, PC Leger, A Greenberg - US Patent App. 17/657,464, 2022 - Google Patents
Abstract Systems and methods for augmenting a data set are provided. An example method
may include locating a foreground object disposed within a seed image, identifying an …
may include locating a foreground object disposed within a seed image, identifying an …
Method and device for controlling a robot
A computer-implemented method for applying control to a robot, and apparatus therefor. A
parametric model of an environment, in particular a deep neural network, is trained in …
parametric model of an environment, in particular a deep neural network, is trained in …
Method and system for removing noise in documents for image processing
KR Kabaria, H Jain - US Patent 11,663,840, 2023 - Google Patents
US11663840B2 - Method and system for removing noise in documents for image processing
- Google Patents US11663840B2 - Method and system for removing noise in documents for …
- Google Patents US11663840B2 - Method and system for removing noise in documents for …