Department of Mathematics and Computer Science

Speaker: Professor James BaileyAbstract: In this seminar, we will review a measure known as Local Intrinsic Dimensionality (LID), which can be used for characterizing the complexity of local neighbourhoods in data. LID can loosely be thought of as a measure for the number of latent variables needed for characterising a particular locality in multi dimensional space. In this talk we will review the LID measure and its uses in machine learning and data mining. In particular, we focus on two recent exciting applications.The first application is in anomaly detection, where we report on a ‘dimensionality-aware’ outlier detection method, DAO, which is derived as an estimator of an asymptotic local expected density ratio involving a query point and a close neighbor drawn at random. DAO significantly outperforms three popular and important benchmark local outlier detection methods.The second application is in the field of self supervised learning, where we show i) how the use of LID for dimensionality regularization at a local level can be used to mitigate an underfilling phenomenon known as dimensional collapse and ii) how the local dimensionality of deep representations can be used as a proxy target when searching for suitable data augmentation policies in contrastive learning. Short Biography: James Bailey is a Professor in the Faculty of Engineering and Information Technology at The University of Melbourne and Program Lead for the University’s Artificial Intelligence Platform. He was previously an Australian Research Council Future Fellow and is a researcher in the field of machine learning and artificial intelligence, including interdisciplinary applications and operational frameworks. His interests particularly relate to the assurance, certification and safety of systems based on machine learning and artificial intelligence. He works on the deployment of AI systems in collaboration with a wide range of industry and government partners across sectors such as defence, energy and health. He is co-General Chair for the Australasian Joint Conference in Artificial Intelligence to be held in Melbourne in December 2024.Read more here: https://findanexpert.unimelb.edu.au/profile/351-james-bailey

Speaker: Michael E. Houle, New Jersey Institute of Technology (NJIT), USAAbstract: Researchers have long considered the analysis of similarity applications in terms of the intrinsic dimensionality (ID) of the data. Although traditionally ID has been viewed as a characterization of the complexity of discrete datasets, more recently a local model of intrinsic dimensionality (LID) has been extended to the case of smooth growth functions in general, and distance distributions in particular, from its first principles in terms of similarity, features, and probability. Since then, LID has found applications — practical as well as theoretical — in such areas as similarity search, data mining, and deep learning. LID has also been shown to be equivalent under transformation to the well-established statistical framework of extreme value theory (EVT). In this tutorial, we will survey some of the wider connections between ID and other forms of complexity analysis, including EVT, power-law distributions, chaos theory, anddynamical systems. We will then see how LID can potentially serve as a unifying framework for the understanding of these theories in the context of machine learning in general, and deep learning in particular.Short Biography: Michael Houle obtained his PhD degree in 1989 from McGill University in Canada, in the area of computational geometry. Since then, he developed research interests in algorithmics, data structures, and relational visualization, first at Kyushu University and the University of Tokyo in Japan, and from 1992 at the University of Newcastle and the University of Sydney in Australia.From 2001 to 2004, while at IBM Japan's Tokyo Research Laboratory, he first began working on approximate similarity search and shared-neighbor clustering methods for data mining applications.From 2004, at the National Institute of Informatics, Tokyo, his research interests expanded to include dimensionality and scalability in the context of fundamental AI / machine learning / data mining tasks such as search, clustering, classification, and outlier detection.In 2021, he relocated to Vancouver, BC, Canada. Currently he is with the New Jersey Institute of Technology in Newark, NJ, USA, and divides his time between Newark and Vancouver.Read more here: https://people.njit.edu/profile/meh43

Speaker: Manuel Del Piano, PhD studentAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.

Speaker: Marika D’Avanzo, PhD studentAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.

Speaker: Sofie Antonia Martins, PhD studentAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.

Speaker: Alessandra D’Alise, PhD studentAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.

We invite high school students to an exciting day celebrating Science Day in the spirit of maths and computer science. The aim is for the day to be both fun and educational, bringing you closer to the subjects and study environment at the University of Southern Denmark and the Department of Mathematics and Computer Science.During the day, there will be two academic workshops, one on maths and one on computer science. All participants will experience both workshops. The teaching will be held by dedicated students from the Department of Mathematics and Computer Science.We finish the day with a conversation café with the students, where you will have the opportunity to hear more about everyday life at a university.

We invite high school students to an exciting day celebrating Science Day in the spirit of maths and computer science. The aim is for the day to be both fun and educational, bringing you closer to the subjects and study environment at the University of Southern Denmark and the Department of Mathematics and Computer Science.During the day, there will be two academic workshops, one on maths and one on computer science. All participants will experience both workshops. The teaching will be held by dedicated students from the Department of Mathematics and Computer Science.We finish the day with a conversation café with the students, where you will have the opportunity to hear more about everyday life at a university.

Speaker: Alessandra D’Alise, PhD studentAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.

Speaker: Giacomo Cacciapaglia, Senior ResearcherAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.

Speaker: Giulia Muco, PhD studentAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.

Speaker: Domenico Frattulillo, PhD studentAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.

This year's special theme: Supervision

This year's special theme: Supervision

Speaker: Mattia Damia Paciarini, PhD studentAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.

Speaker: Antonio Rago, Associate ProfessorAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.

Speaker: Benjamin Jäger, Associate ProfessorAbstract: TBALocation: The DIAS Meetingroom Syd (V22-503a-2)You can also join via Zoom (passcode: 060379).The event is open to all.