BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Biomedical Mathematics Group - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Biomedical Mathematics Group
X-ORIGINAL-URL:https://www.ibs.re.kr/bimag
X-WR-CALDESC:Events for Biomedical Mathematics Group
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:20230101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20241213T130000
DTEND;TZID=Asia/Seoul:20241213T150000
DTSTAMP:20260525T072445
CREATED:20241022T001007Z
LAST-MODIFIED:20241209T042229Z
UID:10190-1734094800-1734102000@www.ibs.re.kr
SUMMARY:Kolmogorov-Arnold Networks - U Jin Choi
DESCRIPTION:In this talk\, we discuss the paper : “KAN: Kolmogorov-Arnold Networks\,” by Z Liu et al. Abstract: Inspired by the Kolmogorov-Arnold representation theorem\, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes (“neurons”)\, KANs have learnable activation functions on edges (“weights”). KANs have no linear weights at all — every weight parameter is replaced by a univariate function parametrized as a spline. We show that this seemingly simple change makes KANs outperform MLPs in terms of accuracy and interpretability. For accuracy\, much smaller KANs can achieve comparable or better accuracy than much larger MLPs in data fitting and PDE solving. Theoretically and empirically\, KANs possess faster neural scaling laws than MLPs. For interpretability\, KANs can be intuitively visualized and can easily interact with human users. Through two examples in mathematics and physics\, KANs are shown to be useful collaborators helping scientists (re)discover mathematical and physical laws. In summary\, KANs are promising alternatives for MLPs\, opening opportunities for further improving today’s deep learning models which rely heavily on MLPs.
URL:https://www.ibs.re.kr/bimag/event/kolmogorov-arnold-networks-u-jin-choi/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20241213T140000
DTEND;TZID=Asia/Seoul:20241213T160000
DTSTAMP:20260525T072445
CREATED:20241209T000818Z
LAST-MODIFIED:20241209T000818Z
UID:10337-1734098400-1734105600@www.ibs.re.kr
SUMMARY:Laplacian renormalization group for heterogeneous networks - Gyuyoung Hwang
DESCRIPTION:In this talk\, we study and discuss the paper “Laplacian renormalization group for heterogeneous networks” by Pablo Villegas et.al\, Nature Physics\, 2023. \nAbstract  \nThe renormalization group is the cornerstone of the modern theory of universality and phase transitions and it is a powerful tool to scrutinize symmetries and organizational scales in dynamical systems. However\, its application to complex networks has proven particularly challenging\, owing to correlations between intertwined scales. To date\, existing approaches have been based on hidden geometries hypotheses\, which rely on the embedding of complex networks into underlying hidden metric spaces. Here we propose a Laplacian renormalization group diffusion-based picture for complex networks\, which is able to identify proper spatiotemporal scales in heterogeneous networks. In analogy with real-space renormalization group procedures\, we first introduce the concept of Kadanoff supernodes as block nodes across multiple scales\, which helps to overcome detrimental small-world effects that are responsible for cross-scale correlations. We then rigorously define the momentum space procedure to progressively integrate out fast diffusion modes and generate coarse-grained graphs. We validate the method through application to several real-world networks\, demonstrating its ability to perform network reduction keeping crucial properties of the systems intact.
URL:https://www.ibs.re.kr/bimag/event/laplacian-renormalization-group-for-heterogeneous-networks-gyuyoung-hwang/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
END:VCALENDAR