HOME /

Presentations

ConvART: Improving Adaptive Resonance Theory for Unsupervised Image Clustering, at CVIS 2018, Tuesday, November 6, 2018
While supervised learning techniques have become increasingly adept at separating images into different classes, these techniques require large amounts of labelled data which may not always be available. We propose a novel neuro-dynamic method for unsupervised image clustering by combining 2 biologically-motivated models: Adaptive Resonance Theory (ART) and Convolutional Neural Networks (CNN). ART networks are unsupervised clustering algorithms that have high stability in preserving learned information while quickly learning new information. Meanwhile, a major property of CNNs is their... Read more about ConvART: Improving Adaptive Resonance Theory for Unsupervised Image Clustering
Breaking Into Deep Learning: 5 projects to get you inspired, at University of Waterloo: Data Science Club, Saturday, November 3, 2018
It's natural to feel lost when you want to start working in a new field. All you need is a little inspiration to get you going in the right direction. We will discuss 5 exciting projects that might spark your interest in one of the many areas of deep learning and give you some ideas of what to work on. Read more about Breaking Into Deep Learning: 5 projects to get you inspired
Making the Most of Graduate Research in AI, at StartAI 2018, Saturday, November 3, 2018
If you're willing to take the pay cut and make the time commitment to go to grad school, then your graduate research better be worth it. To help you find a graduate research topic you can be passionate about, we will discuss the different areas of AI you can study in grad school, the exciting applications being actively developed in these areas, and some of the technical details behind each of them.  Read more about Making the Most of Graduate Research in AI
Deep Learning for Lost Data Restoration and Imputation, at SSC 2018, Monday, June 4, 2018

Lossy, noisy, or missing data are a common phenomena in many areas of statistics ranging from sampling to statistical learning. Instead of just ignoring these missing values, it can be useful to somehow attempt to recover or impute them. Meanwhile, deep learning is increasingly shown to be adept at learning latent representations or distributions of data. These patterns or representations can often be too complex to be recognized manually or through classical statistical techniques. We will discuss practical deep learning approaches to the problem of lossy data restoration or imputation...

Read more about Deep Learning for Lost Data Restoration and Imputation