I'm a postdoc at the Vector Institute, supervised by Sageev Oore, Currently, my focus is on how to infer latent dynamics and drive music synthesis, applying this to therapy for Parkinson's disease.
My previous postdoc was in Morrislab, supervised by Quaid Morris. Before I came to Toronto, I completed my PhD with Amos Storkey in his research group at Edinburgh University. Our work focused on resource efficient machine learning and can be found in this list.
Supervised by Quaid Morris, worked on novel methods for inferring structured discrete latent variables for application in subclonal inference.
Supervised by Amos Storkey and D K Arvind, as part of the Bayeswatch group, my project focused on resource efficiency and architecture search in machine learning. Publications completed during the PhD are:
In the process of my PhD I replicated the work of other papers in the field, such as "Variational Dropout and the Local Reparameterization Trick", "Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization" and "The Shattered Gradients Problem". A more complete list can be found here and my GitHub profile is here. I've also posted reviews of papers on Short Science.
I'm proficient in: Python, C, Verilog, Matlab, Tensorflow, Theano, PyTorch, Lasagne, Bash scripting and Linux.
I developed a dockerised JupyterHub deployment for the Data, Design and Society course to provide students with a fully configured web coding environment.
Also, I marked and tutored courses on machine learning, probabilistic modeling and system design.
During my PhD, I attended the 2015 Gaussian Process Summer School, UK, and was selected to attend the 2016 Machine Learning Summer School, Peru.
I competed in the AES Seizure Prediction Challenge (16th/504) and the National Data Science Bowl (57th/1049) in the team Neuroglycerin. The code written for both competitions is available: hail-seizure and neukrill-net.
This programme was designed as a precursor to a three year PhD project at the Doctoral Training Centre in Neuroinformatics and Computational Neuroscience, providing background in neuroscience and machine learning.
This was a biological data mining project as part of the SynSYS collaboration to investigate synaptic protein-protein interactions supervised by Douglas Armstrong.
Graduated in 2013 - First class with honours.
Also included a 6 month internship at Broadcom Corporation working on analog VLSI as part of my Master's project supervised by Robert Henderson.
Personal Chair of Machine Learning at School of Informatics, University of Edinburgh
D K Arvind
Chair of Distributed Wireless Computation at School of Informatics, University of Edinburgh