公开(公告)号：US10740395B2

公开(公告)日：2020-08-11

申请号：US16727023

申请日：2019-12-26

Applicant: SAS Institute Inc.

Inventor： Henry Gabriel Victor Bequet ,  Jacques Rioux ,  John Alejandro Izquierdo ,  Huina Chen ,  Juan Du

IPC: G06F9/46 ,  G06F16/901 ,  H04L29/08 ,  G06F16/903

Abstract: An apparatus includes a processor to: train a first neural network of a chain to generate first configuration data including first trained parameters, wherein the chain performs an analytical function generating a set of output values from a set of input values, each neural network has inputs to receive the set of input values and outputs to output a portion of the set of output values, and the neural networks are ordered from the first at the head to a last neural network at the tail, and are interconnected so that each neural network additionally receives the outputs of a preceding neural network; train, using the first configuration data, a next neural network in the chain ordering to generate next configuration data including next trained parameters; and use at least the first and next configuration data and data indicating the interconnections to instantiate the chain to perform the analytical function.

公开(公告)号：US20200133977A1

公开(公告)日：2020-04-30

申请号：US16727023

申请日：2019-12-26

Applicant: SAS Institute Inc.

Inventor： Henry Gabriel Victor Bequet ,  Jacques Rioux ,  John Alejandro Izquierdo ,  Huina Chen ,  Juan Du

IPC: G06F16/901 ,  G06F16/903 ,  H04L29/08

Abstract: An apparatus includes a processor to: train a first neural network of a chain to generate first configuration data including first trained parameters, wherein the chain performs an analytical function generating a set of output values from a set of input values, each neural network has inputs to receive the set of input values and outputs to output a portion of the set of output values, and the neural networks are ordered from the first at the head to a last neural network at the tail, and are interconnected so that each neural network additionally receives the outputs of a preceding neural network; train, using the first configuration data, a next neural network in the chain ordering to generate next configuration data including next trained parameters; and use at least the first and next configuration data and data indicating the interconnections to instantiate the chain to perform the analytical function.

公开(公告)号：US20190384790A1

公开(公告)日：2019-12-19

申请号：US16556573

申请日：2019-08-30

Applicant: SAS Institute Inc.

Inventor： Henry Gabriel Victor Bequet ,  Jacques Rioux ,  John Alejandro Izquierdo ,  Huina Chen ,  Juan Du

IPC: G06F16/901 ,  G06F16/903 ,  H04L29/08

Abstract: An apparatus includes a processor to: train a first neural network of a chain to generate first configuration data including first trained parameters, wherein the chain performs an analytical function generating a set of output values from a set of input values, each neural network has inputs to receive the set of input values and outputs to output a portion of the set of output values, and the neural networks are ordered from the first at the head to a last neural network at the tail, and are interconnected so that each neural network additionally receives the outputs of a preceding neural network; train, using the first configuration data, a next neural network in the chain ordering to generate next configuration data including next trained parameters; and use at least the first and next configuration data and data indicating the interconnections to instantiate the chain to perform the analytical function.

公开(公告)号：US10650045B2

公开(公告)日：2020-05-12

申请号：US16556573

申请日：2019-08-30

Applicant: SAS Institute Inc.

Inventor： Henry Gabriel Victor Bequet ,  Jacques Rioux ,  John Alejandro Izquierdo ,  Huina Chen ,  Juan Du

IPC: G06F9/46 ,  G06F16/901 ,  H04L29/08 ,  G06F16/903

Abstract: An apparatus includes a processor to: train a first neural network of a chain to generate first configuration data including first trained parameters, wherein the chain performs an analytical function generating a set of output values from a set of input values, each neural network has inputs to receive the set of input values and outputs to output a portion of the set of output values, and the neural networks are ordered from the first at the head to a last neural network at the tail, and are interconnected so that each neural network additionally receives the outputs of a preceding neural network; train, using the first configuration data, a next neural network in the chain ordering to generate next configuration data including next trained parameters; and use at least the first and next configuration data and data indicating the interconnections to instantiate the chain to perform the analytical function.