EP 4196916 A1 20230621 - METHOD OF TRAINING A NEURAL NETWORK AND RELATED SYSTEM AND METHOD FOR CATEGORIZING AND RECOMMENDING ASSOCIATED CONTENT
Title (en)
METHOD OF TRAINING A NEURAL NETWORK AND RELATED SYSTEM AND METHOD FOR CATEGORIZING AND RECOMMENDING ASSOCIATED CONTENT
Title (de)
VERFAHREN ZUM TRAINIEREN EINES NEURONALEN NETZWERKS UND ZUGEHÖRIGES SYSTEM UND VERFAHREN ZUR KATEGORISIERUNG UND EMPFEHLUNG VON ZUGEHÖRIGEM INHALT
Title (fr)
PROCÉDÉ D'ENTRAÎNEMENT D'UN RÉSEAU NEURONAL ET SYSTÈME ET PROCÉDÉ ASSOCIÉS POUR CATÉGORISER ET RECOMMANDER UN CONTENU ASSOCIÉ
Publication
Application
Priority
GB 2020052036 W 20200825
Abstract (en)
[origin: WO2022043643A1] A property vector representing extractable measurable properties, such as musical properties, of a file is mapped to semantic properties for the file. This is achieved by using artificial neural networks "ANNs" in which weights and biases are trained to align a distance dissimilarity measure in property space for pairwise comparative files back towards a corresponding semantic distance dissimilarity measure in semantic space for those same files. The result is that, once optimised, the ANNs can process any file, parsed with those properties, to identify other files sharing common traits reflective of emotional- perception, thereby rendering a more liable and true-to-life result of similarity/dissimilarity. This contrasts with simply training a neural network to consider extractable measurable properties that, in isolation, do not provide a reliable contextual relationship into the real-world.
IPC 8 full level
G06N 3/04 (2023.01); G06N 3/08 (2023.01); G10H 1/00 (2006.01)
CPC (source: EP)
G06N 3/045 (2023.01); G06N 3/084 (2013.01); G10H 1/0008 (2013.01); G06N 3/044 (2023.01); G10H 2240/085 (2013.01); G10H 2250/311 (2013.01)
Citation (search report)
See references of WO 2022043643A1
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
Designated validation state (EPC)
KH MA MD TN
DOCDB simple family (publication)
DOCDB simple family (application)
GB 2020052036 W 20200825; EP 20764749 A 20200825