Method for neural network and apparatus performing same method
(57) ABSTRACT A method for operating an artificial neuron and an apparatus for performing
the method are provided. The artificial neu ron may calculate a change amount of an …
the method are provided. The artificial neu ron may calculate a change amount of an …
Generating and identifying functional subnetworks within structural networks
In one aspect, a method includes generating a functional subgraph of a network from a
structural graph of the network. The structural graph comprises a set of vertices and …
structural graph of the network. The structural graph comprises a set of vertices and …
Extracting salient features from video using a neurosynaptic system
Embodiments of the invention provide a method of visual saliency estimation comprising
receiving an input sequence of image frames. Each image frame has one or more channels …
receiving an input sequence of image frames. Each image frame has one or more channels …
Characterizing activity in a recurrent artificial neural network
US11663478B2 - Characterizing activity in a recurrent artificial neural network - Google
Patents US11663478B2 - Characterizing activity in a recurrent artificial neural network …
Patents US11663478B2 - Characterizing activity in a recurrent artificial neural network …
Metadata transfer in audio video systems
S Yarygin, LA Thompson, CB Harrell, G Kim - US Patent 9,769,417, 2017 - Google Patents
Aspects relate to transmission of metadata from a source to a sink device, and optionally
through one or more interme diaries. A source device encodes metadata into what would …
through one or more interme diaries. A source device encodes metadata into what would …
Extracting salient features from video using a neurosynaptic system
Embodiments of the invention provide a method of visual saliency estimation comprising
receiving an input sequence of image frames. Each image frame has one or more channels …
receiving an input sequence of image frames. Each image frame has one or more channels …
Distance metrics and clustering in recurrent neural networks
Distance metrics and clustering in recurrent neural networks. For example, a method
includes determining whether topological patterns of activity in a collection of topological …
includes determining whether topological patterns of activity in a collection of topological …
Encrypting and decrypting information
US11569978B2 - Encrypting and decrypting information - Google Patents US11569978B2 -
Encrypting and decrypting information - Google Patents Encrypting and decrypting information …
Encrypting and decrypting information - Google Patents Encrypting and decrypting information …
Extracting motion saliency features from video using a neurosynaptic system
Embodiments of the invention provide a method of visual saliency estimation comprising
receiving an input video of image frames. Each image frame has one or more channels, and …
receiving an input video of image frames. Each image frame has one or more channels, and …
Output from a recurrent neural network
Application of the output from a recurrent artificial neural network to a variety of different
applications. A method can include identifying topological patterns of activity in a recurrent …
applications. A method can include identifying topological patterns of activity in a recurrent …