METHODS FOR TRAINING DEEP CONVOLUTIONAL NEURAL NETWORKS BASED ON DEEP LEARNING

FIELD: computing technology.SUBSTANCE: invention relates to a method for building a classifier of pathogenicity of variants. Also to a method for building a classifier based on a convolutional neural network for classifying variants, implemented by means of a computer, to computer-readable long-term...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	SUNDARAM, Laksshman, MAKREJ, Dzheremi Frensis, FARKH, Kaj-Khou, GAO, Khun
Format:	Patent
Sprache:	eng ; rus
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	FIELD: computing technology.SUBSTANCE: invention relates to a method for building a classifier of pathogenicity of variants. Also to a method for building a classifier based on a convolutional neural network for classifying variants, implemented by means of a computer, to computer-readable long-term information storage media and systems including one or multiple processors associated with memory.EFFECT: provided classification of pathogenicity of variants by means of a neural network.23 cl, 1 ex, 66 dwg, 8 tbl Изобретение относится к способу построения классификатора патогенности вариантов. А также к способу построения классификатора на основе сверточной нейронной сети для классификации вариантов, реализуемому при помощи компьютера, компьютерочитаемым носителям долговременного хранения информации и системам, включающим один или несколько процессоров, связанных с памятью. 6 н. и 17 з.п. ф-лы, 1 пр., 66 ил., 8 табл.