Open Access. Powered by Scholars. Published by Universities.®

Computer Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Software

Technological University Dublin

Articles 1 - 5 of 5

Full-Text Articles in Computer Engineering

Activist: A New Framework For Dataset Labelling, Jack O'Neill, Sarah Jane Delany, Brian Mac Namee Sep 2016

Activist: A New Framework For Dataset Labelling, Jack O'Neill, Sarah Jane Delany, Brian Mac Namee

Conference papers

Acquiring labels for large datasets can be a costly and time-consuming process. This has motivated the development of the semi-supervised learning problem domain, which makes use of unlabelled data — in conjunction with a small amount of labelled data — to infer the correct labels of a partially labelled dataset. Active Learning is one of the most successful approaches to semi-supervised learning, and has been shown to reduce the cost and time taken to produce a fully labelled dataset. In this paper we present Activist; a free, online, state-of-the-art platform which leverages active learning techniques to improve the efficiency of dataset labelling ...


Activist: A New Framework For Dataset Labelling, Jack O'Neill, Sarah Jane Delany, Brian Macnamee Sep 2016

Activist: A New Framework For Dataset Labelling, Jack O'Neill, Sarah Jane Delany, Brian Macnamee

Conference papers

Acquiring labels for large datasets can be a costly and time-consuming process. This has motivated the development of the semi-supervised learning problem domain, which makes use of unlabelled data — in conjunction with a small amount of labelled data — to infer the correct labels of a partially labelled dataset. Active Learning is one of the most successful approaches to semi-supervised learning, and has been shown to reduce the cost and time taken to produce a fully labelled dataset. In this paper we present Activist; a free, online, state-of-the-art platform which leverages active learning techniques to improve the efficiency of dataset labelling ...


Measuring The Effectiveness Of Software-Based Training To Improve The Spatial Visualization Skills Of Students In Stem Disciplines In Higher Education Institutions, Peter Cole Jan 2016

Measuring The Effectiveness Of Software-Based Training To Improve The Spatial Visualization Skills Of Students In Stem Disciplines In Higher Education Institutions, Peter Cole

Dissertations

This research investigates how software can be used to teach spatial skills leading to greater success in Science, Technology, Engineering, and Mathematical (STEM) fields. Existing research indicates that spatial skills can be taught and that good spatial skills are common to people who succeed in STEM fields. In this work, a software-only testing system with a direct targeted, training intervention module was implemented to measure and teach spatial skills using mental rotations, which are believed to be one of the most significant indicators of success in STEM fields. Spatial skills were tested using a standardized and validated test that measures ...


Hardware/Software Codesign, Richard Gallery Nov 2015

Hardware/Software Codesign, Richard Gallery

The ITB Journal

The current state of the art technology in integrated circuits allows the incorporation of multiple processor cores and memory arrays, in addition to application specific hardware, on a single substrate. As silicon technology has become more advanced, allowing the implementation of more complex designs, systems have begun to incorporate considerable amounts of embedded software [3]. Thus it becomes increasingly necessary for the system designers to have knowledge on both hardware and software to make efficient design tradeoffs. This is where hardware/software codesign comes into existence.


Non Deterministic Processing In Neural Networks : An Introduction To Multi-Threaded Neural Networks, Stephen Sheridan Nov 2015

Non Deterministic Processing In Neural Networks : An Introduction To Multi-Threaded Neural Networks, Stephen Sheridan

The ITB Journal

Since McCullough and Pitts first published their work on the Binary Decision Neuron much research has been accumulated in the area of neural networks. This work has for the most part centred on network topologies and learning algorithms. The neural networks that have found their way into devices such as handheld PC’s are the fruit of NN research that has spanned 57 years. There is a simplistic beauty in the way that artificial neural networks model the biological foundations of the human thought process, but one piece of the jigsaw puzzle is still missing. We have so far been ...