Professor Weibo Gong IEEE Fellow Distinguished University Professor University of Massachusetts, Amherst |
Weibo Gong is a University Distinguished Professor of Electrical and Computer Engineering at the University of Massachusetts, Amherst. He received his PhD degree in Engineering Sciences from Harvard University in 1987 and since has been with the University of Massachusetts. He has been working in internet congestion control, wireless network security, and bio-plausible algorithms for artificial general intelligence. The recognition of his work includes the IEEE Transactions on Automatics Control’s George Axelby outstanding paper award, a Semi-plenary lecture at the Conference on Decision and Control, and a best paper runner-up at the IEEE Infocom.
Spatial signal processing algorithms often use pre-given coordinate systems to label pixel positions. These processing algorithms are thus burdened by an external reference grid, making the acquisition of relative, intrinsic features diļ¬cult. This contrasts to animal vision and cognition: animals recognize features without an external coordinate system. We show that a coordinate system-independent algorithm for visual signal processing is not only important for animal vision, but also fundamental for concept formation. In this lecture we start with a visual object deformation transfer experiment. We then formulate an algorithm that achieves deformation-invariance with relative coordinates. The lecture concludes with implications for general concept formation.