Processing

Please wait...

Settings

Settings

Goto Application

1. US20220004875 - Automated Construction of Neural Network Architecture with Bayesian Graph Exploration

Office
United States of America
Application Number 16919211
Application Date 02.07.2020
Publication Number 20220004875
Publication Date 06.01.2022
Publication Kind A1
IPC
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
CPC
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
G06N 3/082
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
082modifying the architecture, e.g. adding or deleting nodes or connections, pruning
Applicants Mitsubishi Electric Research Laboratories, Inc.
Inventors Toshiaki Koike-Akino
Ye Wang
Andac Demir
Deniz Erdogmus
Title
(EN) Automated Construction of Neural Network Architecture with Bayesian Graph Exploration
Abstract
(EN)

A system for automated construction of an artificial neural network architecture is provided. The system includes a set of interfaces and data links configured to receive and send signals, wherein the signals include datasets of training data, validation data and testing data, wherein the signals include a set of random number factors in multi-dimensional signals X, wherein part of the random number factors are associated with task labels Y to identify, and nuisance variations S. The system further includes a set of memory banks to store a set of reconfigurable deep neural network (DNN) blocks, hyperparameters, trainable variables, intermediate neuron signals, and temporary computation values including forward-pass signals and backward-pass gradients. The system further includes at least one processor, in connection with the interface and the memory banks, configured to submit the signals and the datasets into the reconfigurable DNN blocks, wherein the at least one processor is configured to execute a Bayesian graph exploration using the Bayes-Ball algorithm to reconfigure the DNN blocks such that redundant links are pruned to be compact by modifying the hyperparameters in the memory banks. The system realizes nuisance-robust variational Bayesian inference to be transferable to new datasets in semi-supervised settings.


Related patent documents