Automated Machine Learning for Predicting Trends in Time Series Data by Kouassi, Kouame

“…It also demonstrates that AutoML techniques such as BOHB are effective to automatically finding a well-performing models for predicting trends in time series data, thus making ML model development more systematic and less error-prone.…”
Get full text

Forecasting energy consumption on mines using machine learning techniques by Esterhuizen, Lohani

Get full text

Group treatment for the parents of children with learning-disabilities : as a means of changing the attitudes of parents towards such children, and the effect of such a change on t... by Vosters, Carly J A

“…[page 127 missing] A research was done on the attitudes of parents towards learning-disabled children and on the behaviour rating of the children by their parents (experiment A) and on group treatment for parents of learning-disabled children (experiment B). …”
Get full text

Reinforcement Learning-based Access Schemes in Cognitive Radio Networks by ElGuindy, Ehab Maged

“…In this thesis, we propose different MAC protocols based on three Reinforcement Learning (RL) approaches, namely Q-Learning, Deep Q-Network (DQN), and Deep Deterministic Policy Gradient (DDPG). …”
Get full text
Get full text
Get full text

Using Supervised Learning Methods to Credit Score Informal Merchants by Kazimoto, Derick

“…This study aims to address this issue by developing data-driven credit scoring models for informal merchants using supervised learning methods. …”
Get full text

Non-linear neurocontrol of chemical processes using reinforcement learning by Hunter, Stephen Leon

Get full text

Unravelling black box machine learning methods using biplots by Rowan, Adriaan

“…This allows the output of the model to be represented by colour coding each point on the biplot plane according to the output of an independently calibrated machine learning model. …”
Get full text

Deep Learning for Multi-Tissue Cancer Classification of Gene Expressions by Khorshed, Tarek

“…We demonstrate how our model can be used for transfer learning to build classifiers for tumors lacking sufficient samples to be trained independently. …”
Get full text
Get full text

Multitask learning and data distribution search in visual relationship recognition by Josias, Shane

Get full text

Neurocontroller development for nonlinear processes utilising evolutionary reinforcement learning by Conradie, Alex van Eck

Get full text

Radar-Based Multi-Target Classification Using Deep Learning by Mashanda, Nyasha Ernest

Get full text

Extractive Text Summarization on Single Documents Using Deep Learning by Mohamed, Shehab Mostafa Abdel-Salam

“…The objective of this thesis is to study the performance of deep learning-based models on text summarization through a series of experiments, and propose “SqueezeBERTSum”, a trained summarization model fine-tuned with the SqueezeBERT encoder which achieved competitive ROUGE scores retaining original BERT model’s performance by 98% with ~49% fewer trainable parameters.…”
Get full text
Get full text

A Machine Learning Approach to Predicting the Employability of a Graduate by Modibane, Masego

“…The aim for the dissertation is to build a machine learning classification model that can predict a students likelihood to become employed, based on their student data (for example, their GPA, degree/s held etc). …”
Get full text

Education leadership learning : the experiences and perceptions of MEder's degree students

Get full text

Phonological awareness and learning to read in Afrikaans : the role of working memory

Get full text

The use of technology to minimise learning barriers for learners with cerebral palsy

Get full text

Predictive Maintenance in Rail Transportation: An Explainable Machine Learning Approach by Mabaso, Nelisa Zamantungwa Sphumelele

Get full text

Predicting household poverty with machine learning methods: the case of Malawi by Chinyama, Francis

“…Area under the Curve, Receiver Operating Characteristic curve, recall, precision, F1 score, Matthews Correlation Coefficient and Cohen's Kappa scores confirmed the classification models' reliability. The study, therefore, established that poverty can be predicted by open-source machine learning algorithms using a substantially reduced number of features with accuracy comparable to using the full feature set. …”
Get full text