An investigation of consensus and performance in distributed systems

Within a tiered or zoned architecture, new business constraints for regional data residency, imply a need for new architectural patterns. These constraints are not arbitrary: they arise directly from customers demand to ensure their confidential data stays within their defined borders unless required otherwise (e.g. data originating in the U.S. is intended for an E.U. entity). An architecturally clean approach is to negotiate the movement of data only at the persistence layer.

Enabling Purchase of Residential Homes at Scale

Properly buys and sells homes directly from consumers. For our business to be successful, we must be able to predict two things when making a home purchasing decision:
? The price it would sell for on the open market
? How much time it will spend on the market to sell at that price
These two variables are correlated: price can affect time-on-market, and time-on-market can affect price. There are many other factors at play as well. In the broader market, these complex real estate decisions are largely made using human judgement, based on experience and expertise.

Real VR Hands and Interaction with Virtual Objects

Serving as the most widely-used body part for communication, hand is a very important tool for human to interact with the world. Especially with the continuing development of virtual reality and augmented reality, hand pose information has gradually become an indispensable component for improving users’ experience in interacting with computing devices. Therefore, this project aims at enabling an expressive virtual hand reconstruction to increase immersion and presence in VR experiences.

Express Scripting Technology: Scratch for SOTI SNAP and IoT

SOTI has developed a software product called SOTI SNAP that is designed to allow anyone to create an app with no programming or technical knowledge. SOTI SNAP allows users to drag and drop widgets onto a canvas and connect them together to create an app. Apps generated with SOTI SNAP have cross platform capabilities, they can run on Android and iOS based devices. Currently SNAP apps that require programming logic, must use JavaScript, but using JavaScript requires technical skills.

Visual attention in deep learning for detection and classification

Visual attention refers to the mechanism of dynamically and selectively focusing on a subset of the visual input stimuli for detailed analysis, which is part of the visual perception process of the early primate vision. It has been successfully integrated into the design and implementation of many artificial visual recognition systems with applications to image classification, object detection, object sequence recognition, as well as image captioning and visual question answering.

Off-Policy Reinforcement Learning (RL) for a Production Robotics Application

Kindred offers eCommerce retailers a solution to assist with rapid order fulfilment from their distribution centres. The solution (SORT) is a combination of a so-called put-wall and a humanoid robot. The robot picks up items from orders, scans them, and puts each item in a cubby of the put-wall according to the scan code. The robot comprises a gripper, a 6-degree-of-freedom arm, and a stereo vision module, as well as other electronics and mechanical housing.

Satellite Solar Radiation Nowcasting

The main duty of Hydro-Québec is to repond efficiently to the energy demand of customers, in a safe and secure way while remaining competitive in the markets as well. The main goal of this start-up project is to support Hydro-Québec in developing a future-oriented energy system by proposing innovative technical solutions. Among these solutions, deep learning has been the final choice. Using a deep learning approach, satellite images, weather model outputs and data from solar radiation measurement stations, will be use for the development of a solar radiation nowcasting model.

Power network transfer capability

Hydro-Québec is a public utility that generates and distributes electricity. Despite selling most of its electricity in Québec, its most lucrative sales are in the neighboring markets. To ensure the best possible quality of service, the transmission system must remain stable, but to maximize profits, the company also wants to increase its transmission capacity to maximize energy exports. The transfer limit is now conservatively estimated based on a certain combination of simulated network configurations.

AI to predict emergency visits is an AI-based predictive analytics platform that goes beyond traditional claims-based risk scores to use all patient-related healthcare data to provide both clinicians and care managers with a full breadth of timely, transparent and accurate predictions of health outcomes. helps value-based providers confidently answer a variety of health-care questions like, which patients are most likely to be readmitted to the hospital? Or which of my patients would most benefit from establishing a relationship with a primary care provider?

Link predicting in court

The company Lexum is an undisputed leader in the development of information retrieval tools for the law - statutes, regulations and decisions of courts and tribunals. The project is to improve a new tool offer by the company. The tool is used to retrieve a list of legal subjects from a factual description. With that list extract, the tool provides a list of potential related document.