Clarifying Questions for Conversational Agents

Many conversational agents blend the functionalities of question-answering and chit-chat into a single system. This lays the foundation for a more interactive type of question-answering models which is the primary focus of the research project. Interaction between a user and the agent allows the user to ask an underdefined or ambiguous question, and, instead of […]

Read More
Communication-Efficient Federated Learning Systems

In distributed computing settings, data privacy is of paramount importance (e.g., mobile or medical devices). Federated Learning (FL) empowered the state-of-the-art deep neural network model to provide AI solutions to clients while keeping the client data private in distributed computing settings. Communication between different devices is one of the main bottlenecks of FL model because […]

Read More
Business Development & Strategy Intern

The project will focus on developing expansion strategies as Doggy Bathroom enters the European market and hosts pop up shops throughout North America. The project will focus on creating business development strategies to aid with the rollout of these projects. The main goal of the company is to continue growing the brand awareness throughout North […]

Read More
Open MIDaaS – Mobile Identity as a Service

I will be working on open MIDaaS project. It stands for Mobile Identity as a Service. The project aims at making a mobile application the centre of user authentication. The app will be like a personal wallet which will store the list of attributes like verified email, address, and phone and credit card numbers. A […]

Read More
Deep Learning Based Approaches to Synthetic Data Generation

Synthetic population generation is the process of combining multiple socioeonomic and demographic datasets from various sources and at different granularity, and downscaling them to an individual level. Although it is a fundamental step for many data science tasks, an efficient and standard framework is absent. In this project, we propose a multi-stage framework called SynC […]

Read More
Contrastive Representation Learning on Temporal Point Process Data

The general goal of this project is to improve the downstream tasks by learning better representations of the data, especially multimodal data pairs, like image/text pairs or user/item interaction pairs. The user/item interaction data plays an important role in e-commerce, and analyzing these data can help improve the banking system, e.g., recommendation, risk control, and […]

Read More
Portable Wireless Interface for Implantable Medical Devices

The recording of brain activity through neural Implantable Medical Devices (IMDs) has a wide range of applications, such as studying brain patterns for seizure detection or brain stimulation to alleviate motor disorders. Some IMDs communicate with an external interface platform, which offloads the recorded data from, programs, and supplies power to the IMD. However, existing […]

Read More
SOTI SNAP – Fully Automated App to PDF Generation Utility

Businesses today struggle with manual operations such as paper-based processes and copying and pasting information from one system to another. These manual operations are costing companies hours of unnecessary labour, which trickles down to customers that are expecting on demand services. SOTI has developed a software product called SOTI SNAP that allows anyone to create […]

Read More
Geometry Projection Based 3D Object Detection

Unmanned aerial vehicles (UAV) have been deployed in many real-world applications such as payload delivery, agricultural laboring, and aerial photography. Based on GPS-based localization algorithms, these drones have achieved many advancements in industry automation. However, since common GPS receivers do not work indoors, an accurate computer vision (CV) technique is required to resolve the problem […]

Read More
The influence of axial substituent on the photoluminescence of boron subphthalocyanines

Canadian public and private researchers have taken an interest in a new class of light-emitting materials, subphthalocyanines, which can produce better colour in OLED smartphone and television screens. The materials can be optimized for specific purposes by using slightly different ingredients in their synthesis, or by reacting them with other ingredients after synthesis, but most […]

Read More