Haku
Viitteet 1-6 / 6
Predicting image social tags using a convolutional neural network
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
Convolutional Neural Networks (CNN) are regarded as the state-of-the-art approach in image classification tasks, i.e. predicting appropriate labels for an image. Active ongoing research in the field has produced methods ...
Support Vector Machine and Deep Learning in Medical Applications
(2017)
Pro gradu -tutkielma
Pro gradu -tutkielma
Deep learning is a new field in machine learning that focuses mainly on deep neural networks. In this thesis, we focus on machine learning and deep learning, present support vector machine and neural networks, and then we ...
Using Machine Learning to Predict Student Performance
(2017)
Pro gradu -tutkielma
Pro gradu -tutkielma
This thesis examines the application of machine learning algorithms to predict whether a student will be successful or not. The specific focus of the thesis is the comparison of machine learning methods and feature engineering ...
Performance analysis : a case study on network management system using machine learning
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
Businesses have legacy distributed software systems which are out of traditional data analysis methods due to their complexities. In addition, the software systems evolve and become complex to understand even with the ...
Predicting Deterioration of Patients in the Intensive Care Unit
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
The massive influx of data in healthcare encouraged the building of data-driven machine learning models in order to improve medical diagnosis and assess patients health status. Thus, gaining knowledge and actionable insights ...
Conceptual design on computer sentencing simulation based on SVM
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
The criminal law in China is a relatively uncertain statutory punishment law, and the judge exercise the equitable discretion within the extent for discretionary action of sentencing. However, influenced by many objective ...