Over the past few years, virtual reality has experienced a remarkable resurgence. Fueled by a proliferation of consumer-level head-mounted display and motion tracking devices, an unprecedented quantity of immersive experiences and content has become available for both desktop and mobile VR platforms. However, the problem of locomotion – human movement through a virtual world – […]
Supervised learning algorithms can be understood not only as a set of techniques for building accurate models of data, but also as design tools that can enable rapid prototyping, iterative refinement, and embodied engagement- all activities that are crucial in the design of new musical instruments and other embodied interactions. Realising the creative potential of […]
In the past several years, there has been a lot of progress on combinatorial optimization. Using techniques in convex optimization, geometry, spectral graph theory and randomization, researchers have developed provably faster algorithms for many classical problems such as linear programming and maximum flow problems. In this talk, I will discuss my work in this area […]
Characterizing the computational complexity of statistical inference problems is an outstanding open problem. This is gaining increasing importance given the ubiquity of large scale data analysis and algorithms in application domains as diverse as genomics, healthcare, finance and social sciences. The hidden clique problem is a prototypical example of an inference problem wherein computational constraints […]
Coloring the Universe: Many images of the Universe are spectacular, but are they “real”? Delving deep into the often-unseen world of how images of astronomy are created, this book provides the reader with a unique behind-the-scenes look at exactly how we get these impressive and important visual slices of our Universe. This book opens a […]
Encoding discrete symbol structures as numerical vectors for neural network computation enables the similarity structure inherent in vectorial representations to yield generalizations that reflect content-similarity in a structure-sensitive fashion. Two examples will be presented. In language understanding, the mapping of arguments from syntactic roles (subject, object, etc.) to semantic roles (agent, patient, etc.) is controlled […]
Two talks from the 37th UW/MS Symposium in Computational Linguistics are featured: Using IGT with INTENT: Automatically Enriching Interlinear Glossed Text (IGT) and Discovering Outcomes via Propensity Score Analysis of Social Media Timelines.
Word embeddings are often constructed with discriminative models such as deep nets and word2vec. Mikolov et al (2013) showed that these embeddings exhibit linear structure that is useful in solving “word analogy tasks”. Subsequently, Levy and Goldberg (2014) and Pennington et al (2014) tried to explain why such linear structure should arise in embeddings derived […]