David Browne
Email:
Pulse-Net: Optimised pruning and compression of Neural Network Structures
Apple’s Siri, Amazon’s Echo and Google Home are standard devices in today’s world, but how do these machines understand different people's voice commands? How does Facebook recognise a face to be tagged? Is somebody sitting at the other end of the internet waiting for us to give the devices a command or move the mouse to tag a friend? Of course not!! So how do these machines understand what we say to them, considering the difference between voices? How does Facebook identify faces when we all look different?
Neural Networks, and more specifically Deep Neural Networks (DNN), have been responsible for recent breakthroughs in the area of Artificial Intelligence including image, object and speech recognition, statistical machine translation and even the world of gaming. Modelled on the neurons in the human brain, these artificial neural networks use fundamental blocks of mathematics. These DNN’s achieve state-of-the-art accuracy on various tasks, but have millions of parameters, which can make them difficult to deploy on computationally-limited devices.
David’s research focuses on the question, “Should the structure of these Networks be static or dynamic?” He and his team have found that the network can be compressed by removing unimportant neurons. This new compressed structure can then be deployed on devices such as mobile phones.
Publications
- Journal: Remote Sensing 2020 ,AuthorsPublication DetailsConference Name:Type:Date: 2020Refereed Original Article
- Conference Name: 27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science ,Authors
David Browne, Steven Prestwich, Michael Giering
Publication DetailsType:Proceedings: http://ceur-ws.org, Date: 2019Location: Ireland,Refereed Conf./Meeting Proceeding - Conference Name: IEEE IoT World Forum 2019 ,Authors
David Browne, Steven Prestwich, Michael Giering
Publication DetailsType:Proceedings: https://ieeexplore.ieee.org, Date: 2019Location: Ireland,Refereed Conf./Meeting Proceeding - Conference Name: 11th Multi Conference on Computer Science and Information Systems (MCCSIS) ,Authors
David Browne, Carlo Manna, Steven Prestwich
Publication DetailsType:Proceedings: IADIS International Conference Big Data Analytics, Data Mining and Computational Intelligence 2017 (part of MCCSIS 2017) , Date: 2017Location: Portugal,Refereed Conf./Meeting Proceeding - Conference Name: 24th Irish Conference on Artificial Intelligence and Cognitive Science (AICS) 2016 ,Authors
David Browne, Carlo Manna, Steven Prestwich
Publication DetailsType:Proceedings: to be appear, Date: 2016Location: Ireland,Refereed Conf./Meeting Proceeding
Presentations
- Publication DetailsInsight Researchers: David Browne, Steven PrestwichNon-Insight Researchers: Michael GieringOrganising Body: NUI Galway, Event: AICS 2019, Venue: NUI GalwayDate: 05/12/2019Event Type: ConferencePresentation Type: Paper
- Publication DetailsInsight Researchers: Eugene Freuder, Steven Prestwich, David Browne, Barry O'SullivanEvent: The Third Workshop on Progress Towards the Holy Grail, Date: 30/09/2019Event Type: WorkshopPresentation Type: Oral Presentation
- Publication DetailsInsight Researchers: David Browne, Steven PrestwichNon-Insight Researchers: Michael GieringOrganising Body: IEEE 5th World Forum on Internet of Things, Event: IEEE 5th World Forum on Internet of Things, Venue: LimerickDate: 18/04/2019Event Type: ConferencePresentation Type: Paper
- Publication DetailsInsight Researchers: David BrowneOrganising Body: MCCSIS, Event: International Conference on Big Data Analytics, Data Mining and Computational Intelligence, Venue: LisbonDate: 23/07/2017Event Type: ConferencePresentation Type: Paper