Policy Optimization in Parameter Space

Model-free Reinforcement Learning (RL) has recently demonstrated its great potential in solving difficult intelligent tasks. However, developing a successful RL model requires an extensive model tuning and tremendous training samples. Theoretical analysis of these RL methods, more specifically policy optimization methods, only stay in a simple setting where the learning happens in the policy space. […]

Read More
Package Delivery Robot Interface Research and Development

Postmates has a successful software business in numerous cities in the short-distance package delivery business, matching the vendor (for example, a restaurant, shop or other retail business) with the recipient of a package (for example, groceries, a hot meal, or an envelope), and then contracting with individual couriers (in cars, bikes or on foot) in […]

Read More
Machine learning approaches for event prediction, relation modeling, and inference

Machine learning approaches are transforming fields such as finance, healthcare, electronic commerce, social networks, and natural disaster forecasting. We propose collaborative research that develops novel methods and applications of machine learning techniques for event prediction, modeling relations between entities, and inference techniques that can impact these domains. In the context of event prediction, we will […]

Read More
Scalable Secure Authentication in Mesh-enabled Networks for Smart Cities

The proposed solution will address the aforementioned challenges by attempting to provide scalable authentication and encryption mechanisms. A combination of software and hardware based approaches can be used to provide enhanced security to constrained IoT nodes with respect to their timing and power demands. Technologies such as Bluetooth or 802.11ax mesh networking could be critical […]

Read More
Visualization of gene structures, phylogenetic trees, and RNA structures

Bioinformatics is at the intersection of computer science, mathematics and biology. With the advent of new technologies, more and more genomic data is being generated. A common task for analysing such data is to visualize it in an interactive way that highlights the results of computational analyses. In the past 5 years, Web browsers have […]

Read More
Ultra-low power wireless sensor node design for health monitoring

In this project we address the problem of power consumption for wireless sensor nodes. This is where among different components of a sensor, RF transceivers consume a significant amount of power e.g. approximately 80%. Hence the main objective is this project is to tackle the power consumption problem at the RF transmitter, where we aim […]

Read More
Uncertainty Modeling and Quantification in Neural Network Image Denoisers

Image denoising is a fundamental process in most of computer vision systems, imaging systems, and photography productions. Recently, with the power of deep neural networks, image denoising has been pushed towards new boundaries. However, neural network image denoisers are constrained by the accuracy of the noise model used to train them. Training on a poor […]

Read More
Optical Variable Effects for Minting Applications

The appearance of polished gold and silver has always been attractive to the human eye. The high reflectivity of these surfaces naturally makes them strong candidates for optical designs that are based purely on reflective optics. When circular grooves are scribed into metal surfaces, some very interesting optical effects can be observed, and in some […]

Read More
Technologically Assisted Mindfulness Meditation for Older Adults

Mindfulness meditation has recently received considerable interest in clinical and in broader contexts for its mental health and cognitive benefits. It has been proposed that giving people feedback about their meditation relevant brain activity during or after meditation can help people learn this difficult skill, and initial work looks promising, but there are a number […]

Read More
The Development of an Improved Model for Start-up Accelerators

The goal of this study will be to develop a new and improved model for start-up accelerators. These accelerators can be defined as programs that help start-ups develop their business model and acquire capital such that they can grow and thrive in today’s business environment. To create the new model, start-ups that are part of […]

Read More
Mobile Mesh Technology For Improved Connectivity In Canada

Lack of affordable, reliable access to the Internet in remote, rural, and Indigenous communities in Canada and internationally has led to a digital divide affecting billions. Left has developed its RightMesh technology, which lets nearby mobile devices connect without the Internet. Normally data flows from a phone, through Internet Service Providers (Telus, Shaw), to the […]

Read More