|
US2021027163A1
|
|
Self-organizing partially ordered networks and soft-tying learned parameters, such as connection weights
|
|
WO2021061401A1
|
|
Selective training of deep learning modules
|
|
WO2021040944A1
|
|
Deep learning with judgment
|
|
US2020327414A1
|
|
Stacking multiple nodal networks
|
|
WO2020046719A1
|
|
Self-supervised back propagation for deep learning
|
|
US2020387794A1
|
|
Building a deep neural network with diverse strata
|
|
WO2020036847A1
|
|
Building deep learning ensembles with diverse targets
|
|
WO2020041026A1
|
|
Efficiently building deep neural networks
|
|
WO2020033645A1
|
|
Companion analysis network in deep learning
|
|
US2020410090A1
|
|
Robust von neumann ensembles for deep learning
|
|
WO2020018279A1
|
|
Building ensembles for deep learning by parallel data splitting
|
|
US2021027147A1
|
|
Forward propagation of secondary objective for deep learning
|
|
US2020410295A1
|
|
Analyzing and correcting vulnerabilities in neural networks
|
|
US2020394521A1
|
|
Using back propagation computation as data
|
|
EP3701351A1
|
|
Self-organizing partially ordered networks
|
|
WO2019067831A1
|
|
Multi-objective generators in deep learning
|
|
WO2019067960A1
|
|
Aggressive development with cooperative generators
|
|
US2020210812A1
|
|
Joint optimization of ensembles in deep learning
|
|
US2019095798A1
|
|
Stochastic categorical autoencoder network
|
|
EP3646252A1
|
|
Selective training for decorrelation of errors
|
