Loading Events
Find Events

Event Views Navigation

Past Events › Research Seminar

Events List Navigation

February 2020

Research Seminar – Deepak Padmanabhan (Queen’s University Belfast) – Fairness in Unsupervised Machine Learning: From Political Philosophy to Data Science

February 5 @ 1:00 pm - 2:00 pm
N108, Sir Ian Wood Building

Abstract: Data science has long considered learning better models and making better decisions based on existing data. With data science systems penetrating into every aspect of daily life, whether it be navigation systems that influence which route you pick for your commute or personalized news delivery systems that decide what kind of news you would like to read, it is increasingly critical to consider questions on fairness. For example, would you be more prone to pre-emptive checks at the hands…

Find out more »
December 20192019

Research Seminar – Hubert Shum (Northumbria University) – Human Motion Understanding for Visual Computing

December 4, 2019 @ 1:00 pm - 2:00 pm
N336, Sir Ian Wood Building

Due to the advancement in human motion capturing technology and the availability of public human motion database, human motion understanding has become a core component of many research problems in multiple research domains. In computer graphics, a good representation of human motion facilitates characters with realistic movement, intuitive ways of crowd controls, and the real-time processing of captured motion data. In computer vision, modelling human motion is a key process for effective action classification and gait analysis. The core problem…

Find out more »
November 2019

Research Discussion

November 20, 2019 @ 1:00 pm - 2:00 pm
N310, Sir Ian Wood Building

Internal school discussion about upcoming research opportunities .

Find out more »

Research Seminar – Tom Inns (cofink Ltd) – TBC

November 13, 2019 @ 1:00 pm - 2:00 pm
N336, Sir Ian Wood Building

TBC

Find out more »

Research Seminar – James Littlejohn (Dsensor.org) – The DIY HealthScience Toolkit, Mobile and Peer-to-Peer Network

November 6, 2019 @ 1:00 pm - 2:00 pm
N336, Sir Ian Wood Building

The talk will demo the DIY HealthScience toolkit based on real data from wearable and Luftdaten air quality sensors. The rest of the talk will introduce the technology used to design the user experience, perform the data science and the use of cryptography to create the KBLedger (knowledge Bundle Ledger) that guarantees data interoperability and computational compatibility.

Find out more »
October 2019

Research Seminar – Thanh Nguyen – Multi-label Classification on Data Stream

October 30, 2019 @ 1:00 pm - 2:00 pm
N105, Sir Ian Wood Building

Many batch learning algorithms have been introduced for offline multi-label classification (MLC) over the years. However, the increasing data volume in many applications such as social networks, sensor networks, and traffic monitoring has posed many challenges to batch MLC learning. For example, it is often expensive to re-train the model with the newly arrived samples, or it is impractical to learn on the large volume of data at once. The research on incremental learning is therefore applicable to a large…

Find out more »

Research Seminar – David Noble (Aventus Ai) – AI Driven Asset Integrity For Intelligent Digital Twin Development

October 23, 2019 @ 1:00 pm - 2:00 pm
N311, Sir Ian Wood Building

TBC

Find out more »

Research Seminar – Adamu Ali-Gombe – Learning from Small and Imbalanced Dataset of Images using Generative Adversarial Neural Networks

October 16, 2019 @ 1:00 pm - 2:00 pm
N336, Sir Ian Wood Building

The performance of deep learning models is unmatched by any other approach in supervised computer vision tasks such as image classification. However, training these models require a lot of labelled data which are not always available. Labelling a massive dataset is largely a manual and very demanding process. Thus, this problem has led to the development of techniques that bypass the need for labelling at scale. Despite this, existing techniques such as transfer learning, data augmentation and semi-supervised learning have…

Find out more »

Research Discussion

October 9, 2019 @ 1:00 pm - 2:00 pm
N336, Sir Ian Wood Building

Internal school discussion about upcoming research opportunities .

Find out more »

Research Seminar – Kyle Martin – The Wonderful World of Deep Metric Learning

October 2, 2019 @ 12:00 pm - 1:00 pm
N106, Sir Ian Wood Building

Deep Metric Learners (DMLs) are a group of neural network architectures which learn to optimise case representations for similarity-based return by training upon multiple cases simultaneously to incorporate relationship knowledge. In this talk, I offer a brief introduction to the wonderful world of deep metric learning, and explore some of the work we have been doing with these neural architectures. In particular, we will examine the technical difficulties involved with training these networks, and how techniques from Case-based reasoning research…

Find out more »