Digital image processing using convolutional neural networks

A Ravindran, O Celik-Tinmaz, M Badawy - US Patent 9,524,450, 2016 - Google Patents
According to an example, a digital image may be processed by an ensemble of
convolutional neural networks (CNNs) to classify objects in the digital image. For each CNN …

Generating acoustic models

AW Senior, H Sak, KK Rao - US Patent 9,786,270, 2017 - Google Patents
Graves et al.“Speech Recognition with Deep Recurrent Neural Networks,” ar**
H Sak, SM Shannon - US Patent 10,706,840, 2020 - Google Patents
Methods, systems, and apparatus for performing speech recognition. In some
implementations, acoustic data repre senting an utterance is obtained. The acoustic data …

Image analysis neural network systems

A Jain, S Sankaranarayanan, DS Diwinsky… - US Patent …, 2020 - Google Patents
(57) ABSTRACT A method includes determining object class probabilities of pixels in a first
input image by examining the first input image in a forward propagation direction through …

Noise-enhanced convolutional neural networks

K Audhkhasi, B Kosko, O Osoba - US Patent 11,256,982, 2022 - Google Patents
(57) ABSTRACT A learning computer system may include a data processing system and a
hardware processor and may estimate param eters and states of a stochastic or uncertain …

Implementing a whole sentence recurrent neural network language model for natural language processing

Y Huang, A Sethy, K Audhkhasi… - US Patent …, 2020 - Google Patents
(57) ABSTRACT A computer selects a test set of sentences from among sentences applied
to train a whole sentence recurrent neural network language model to estimate the …

Training of artificial neural networks using safe mutations based on output gradients

JA Lehman, KO Stanley, JM Clune - US Patent 10,699,195, 2020 - Google Patents
Systems and methods are disclosed herein for ensuring a safe mutation of a neural network.
A processor determines a threshold value representing a limit on an amount of diver gence …

Systems and methods for detecting malware using machine learning

A Gardner, W Bogorad, J Mao - US Patent 10,250,617, 2019 - Google Patents
ABSTRACT A computer-implemented method for detecting malware using machine learning
may include (1) identifying data to be analyzed for malware,(2) classifying, using a classifier …

System and method for improved server performance for a deep feature based coarse-to-fine fast search

JH Hsiao, J Li - US Patent 11,275,747, 2022 - Google Patents
Disclosed are systems and methods for improving interac tions with and between computers
in a search system supported by or configured with search servers or platforms. The systems …