EP 3469521 A1 20190417 - NEURAL NETWORK AND METHOD OF NEURAL NETWORK TRAINING
Title (en)
NEURAL NETWORK AND METHOD OF NEURAL NETWORK TRAINING
Title (de)
NEURONALES NETZWERK UND VERFAHREN ZUM TRAINIEREN EINES NEURONALEN NETZWERKS
Title (fr)
RÉSEAU NEURONAL ET PROCÉDÉ D'APPRENTISSAGE DE RÉSEAU NEURONAL
Publication
Application
Priority
- US 201615178137 A 20160609
- US 201715449614 A 20170303
- US 2017036758 W 20170609
Abstract (en)
[origin: WO2017214507A1] A neural network includes inputs for receiving input signals, and synapses connected to the inputs and having corrective weights organized in an array. Training images are either received by the inputs as an array or codified as such during training of the network. The network also includes neurons, each having an output connected with at least one input via one synapse and generating a neuron sum array by summing corrective weights selected from each synapse connected to the respective neuron. Furthermore, the network includes a controller that receives desired images in an array, determines a deviation of the neuron sum array from the desired output value array, and generates a deviation array. The controller modifies the corrective weight array using the deviation array. Adding up the modified corrective weights to determine the neuron sum array reduces the subject deviation and generates a trained corrective weight array for concurrent network training.
IPC 8 full level
G06N 3/02 (2006.01); G06N 3/08 (2023.01); G06F 17/16 (2006.01)
CPC (source: EP KR US)
G06N 3/045 (2023.01 - KR); G06N 3/065 (2023.01 - EP KR); G06N 3/08 (2013.01 - EP KR US); G06N 3/045 (2023.01 - EP)
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated extension state (EPC)
BA ME
DOCDB simple family (publication)
WO 2017214507 A1 20171214; CN 109416758 A 20190301; EP 3469521 A1 20190417; EP 3469521 A4 20200226; JP 2019519045 A 20190704; JP 7041078 B2 20220323; KR 102558300 B1 20230721; KR 20190016539 A 20190218
DOCDB simple family (application)
US 2017036758 W 20170609; CN 201780035716 A 20170609; EP 17811082 A 20170609; JP 2018564317 A 20170609; KR 20197000226 A 20170609