General Machine Learning Practices Using Python
Year: 2019
Type: dissertation
Abstract: Machine Learning (ML), is a process of teaching an algorithm to learn. Algorithms try to find patterns from data to generalise a rule or relation to predict future unseen instances. Some of the popular results of machine learning systems are Google Translate, YouTube’s Video Recommendation System, Movie Recommendation System. \nThe aim of the thesis was to introduce the readers the concept of ML and the phases of the ML model development process as well as their implementation in the Python programming language. \nDifferent categories of ML with examples, typical phases in an ML modelling \nhave been explained in theory in the thesis. In addition, pre-processing data, training and testing models, optimization of a model in the supervised machine learning have been further elaborated using Linear Regression and K-Nearest Neighbor (KNN) as examples in Python programming language. \nThe paper, as a result, can act as a starting tool and conventional guide to a beginner ML practitioner for any ML algorithms other than presented in the paper. People with knowledge of Python can further benefit from the conventions and alternatives presented in the coding section of the paper.
Source: Theseus (Ammattikorkeakoulujen)
Author: Nibesh Khadka
Institution: Oulu University of Applied Sciences
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2953009312
