Institutional Repository of Vilnius University
TensorFlow panaudojimas biologiniams duomenims tirti /
Abstract
dc:descriptionArtificial neuron is a mathematical function that can imitate operation of biological neuron. Neural network consists of many artificial neurons. Neural network is a type of machine learning. Neural networks are capable of completing many various tasks. Neural netowrks need to be trained using related data. Neural networks can be used for biological data analysis. TensorFlow is neural network framework created by Google. TensorFlow can be used to calculate machine learning related calculations in paralel using graphical processors to reduce time needed for calculations. It was decided to use TensorFlow for biological data analysis. An article that describes biological data analysis using machine learning algotythms was taken. Goal of this work is to repeat analysis using TensorFlow and compare results. Even though neural network accuracy measures were slightly different, general conclusion is very similar. Neural networks that consists of two hidden layers got the best accuracy while being used for biological molecules clasification. TensorFlow can be used for biological data analysis.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2018
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Baranauskas, Mantvydas,
- Contributors dc:contributor
-
- Grinis, Irus
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD29420085&prefLang=en_US