AI talk: Multiplex network optimization: capturing cognition and attention

I will examine how procedures for optimally searching through "multiplex" networks (networks made of multiple simple graphs) capture human learning and search patterns. Prior work on semantic memory (people's memory for facts and concepts) has primarily focused on modeling similarity judgments of pairs of words as distances between points in a high-dimensional space (e.g., LSA by Landauer et al, 1998; Word2Vec by Mikolov et al. 2013).

Precision Medicine Studies: Examination of Variants within the Gene: SLC5A2

As biobanks continue to grow and more and more human genomes are sequenced, our ability to detect relationships between genetic variants and diseases is at an unprecedented level. The exponential growth of biological data, including both genetic and health record data, has led to the development of association-based studies (GWAS and PheWAS) that paved the way for identifying links between genetic variations and the development of diseases.

Seeing the Unseen: Data-Driven 3D Scene Understanding

Seeing the Unseen: Data-Driven 3D Scene Understanding
Abstract: Intelligent robots require advanced vision capabilities to perceive and interact with the real physical world. While computer vision has made great strides in recent years, its predominant paradigm still focuses on analyzing image pixels to infer 2D output representations (bounding boxes, segmentations, etc.), which remain far from sufficient for real-world robotics applications.


Subscribe to UW-Madison Computer Sciences Department RSS