Events

Entrepreneurship Capstone Bootcamp

AWS Workshop – How to Hack the Tech Interview

ARISE Program – Validate

Duality of Research: The Academic and Commercial Perspective

Create4Good 2023/2024 Showcase Day

Catholic Junior College – Python Programming with the Raspberry Pi Workshop

It has long been suggested that the biological brain operates at some critical point between two different phases, possibly order and chaos, to maximize the information processing power. Investigating the same hypothesis on the ‘artificial’ brains, i.e. the modern computer vision models, we find that they exhibits the same pattern, i.e. highest test accuracy or lowest test loss at the edge of chaos. A theoretical investigation demonstrates that, the best performance is attributed to the maximal metastable states/periodic cycle length near the edge of chaos, where each metastable state can represent an information point. Applied on a very simple network equivalent of the SK spin glass model and Fashion MNIST dataset, we illustrate a simple and principled training method that can achieve both high accuracy and prevent fitting noisy labels automatically.

VIE Connects

Decentralized Gap Funding 2nd Call for Applications

DH Asia Webinar Series: “The Diaries of the Soviet Ambassador in Pyongyang: Data-Specific Network Approaches to North Korean History Studies” by Dr. Donghyun Woo