Sort by
Refine Your Search
-
known as Team COMPAS -- includes a number of amazing undergraduate and graduate students, postdocs, alumni, and other fantastic collaborators. Please contact me if you are interested in joining our group
-
This project aims to employ advanced machine learning techniques to analyse text, audio, images, and videos for signs of harmful behaviour. Natural language processing algorithms are utilized
-
formula is true or false (EXPTIME vs NP). Can we develop and implement efficient algorithms for this problem? This problem has been attacked using multiple different methods for the past 40 years, without
-
The existing deep learning based time series classification (TSC) algorithms have some success in multivariate time series, their accuracy is not high when we apply them on brain EEG time series (65
-
challenging data problem. Weak signals from collisions of compact objects can be dug out of noisy time series because we understand what the signal should look like, and can therefore use simple algorithms
-
software frameworks, algorithms, robust testing and validation methods, and/or empirically validated solutions that contribute directly to social good, promoting trust, fairness, transparency, and
-
determined by combining the observed space density of galaxies, the measured spatial distribution of galaxies and simulations of the dark matter distribution. Example themes for student projects follow and
-
the given non-classical logic. The proof of the claim contains an algorithm for deciding whether an arbitrary formula is true or else false! This proof can then be exported automatically to produce a formally
-
-readable representations, such as distributed representations of text augmented with random noises [1] or unnatural text curated by replacing sensitive tokens with random non-sensitive ones [2]. First, such
-
distributions. We wish to represent the biological networks into proper formats, e.g., vector representations, so that existing machine learning algorithms (e.g., support vector machines) can readily be used