Media
CMU ML Lunch (May 12): Alona Fyshe
Speaker: Alona Fyshe Title: Interpretable Semantic Vectors from a Joint Model of Brain- and Text- Based Meaning Abstract Vector space models (VSMs) represent word meanings as points in a high dimensional space. VSMs are typically created using a large text corpora, and so represent word semantics as observed in text. We present a new algorithm (JNNSE) that can incorporate a measure of semantics not previously used to create VSMs: brain activation data recorded while people read words. The resulting model takes advantage of the complementary strengths and weaknesses of corpus and brain activation data to give a more complete representation of semantics. Evaluations show that the model 1) matches a behavioral measure of semantics more closely, 2) can be used to predict corpus data for unseen words and 3) has predictive power that generalizes across brain imaging technologies and across subjects. We believe that the model is thus a more faithful representation of mental vocabularies. Joint work with Partha Talukdar, Brian Murphy and Tom Mitchell For more ML lunch talks, visit http://www.cs.cmu.edu/~learning/
Surviving your first year on the tenure track
How to start a research lab
Science MagOnline
Three U of A researchers named national artificial intelligence chairs
Researchers turning to social media to study mental health concerns during the pandemic
Biography
Alona Fyshe is an Assistant Professor in the Computer Science Department at the University of Victoria and a CIFAR Global Scholar. Fyshe received her BSc and MSc in Computing Science from the University of Alberta, and a PhD in Machine Learning from Carnegie Mellon University. Fyshe uses machine learning to leverage large amounts of text and neuroimaging data to understand how people mentally combine words to create higher-order meaning.
Recognition/Reconnaissance
Canadian Institute For Advanced Research Global Scholar | Professional
The CIFAR Global Scholar award funds researchers within five years of their first academic appointment, helping them build research networks and develop essential skills needed to become leaders in global research https://www.cifar.ca/assets/inaugural-cifar-azrieli-global-scholars-appointed/
Past Talks
The Semantics of Phrases and Sentences in the Human Brain
Research Seminar
University of British Columbia, September 5, 2014
Interpretable Semantic Vectors from a Joint Model of Brain- and Text- Based Meaning
Machine Learning Lunch
Carnegie Mellon University, May 12, 2014
Corpora, Cognition and Composition: Exploring Semantics in the Human Brain
CLSP Seminar
Johns Hopkins University, February 17, 2016
Decoding semantics from phrases and sentences using magnetoencephalography.
BioMAG
Halifax, NS, August 26, 2014