Ubisoft records the interaction between its customers and its servers in large execution logs (also called traces). Any failure of the system is thus recorded therein. However, the considerable size of these logs considerably hinders their effective use by analysts and developers. We propose an automated method to detect failing executions, and furthermore to characterize the features that are common to clusters of failing instances. The approach will be based an machine learning algorithms, and will produce clusters of failing traces with common features.
Ciena is a Canadian company leader in engineering and manufacturing networking systems and devices. The company has around 5,000 operable products in its portfolio. The vast majority of Ciena products generate logs during the boot up and the mission mode operations from the various tasks running on their real time operating systems. The company wants thus to increase its software’s capabilities in order to be able to collect any type of log data generated in the production site and linked to other external information to extract actionable knowledge.
This project seeks to explore the use of a class of artificial intelligence algorithms called reinforcement learning for the purpose of aiding the training of new pilots. In the process, we seek to “teach” an algorithm how to fly an aircraft by exposing the AI pilot to a virtual environment and providing it with flight data and a goal. Alternatively, the algorithm could learn by observing human pilots.
We’d like to address the issue of 3D reconstruction from 2D images. This means developing a machine learning algorithm that can take a regular photo as an input and generate a full 3-dimensional reconstruction of the contents of the photo. Such technology can be used creatively or to help the coming generation of robots better understand their surroundings.
Assessment of surgical data from an operating room is a complex process that may require significant resources such as expert input and advanced technology. Automation brings a considerable opportunity to greatly reducing these significant resource requirements - e.g., using computer vision software to detect clinically relevant actions during surgery. However, those detections should be interpretable, or more actionable in order to be audited or reviewed.
Since the introduction of radio and television, fans have had a connection to those they know in the media. These connections are called âparasocial relationshipsâ and they are one-sided relationships, usually between a fan and a celebrity, that is usually not face-to-face. With the advent of social media, any person, or company, can become a celebrity and gain fans.
Given the current global environmental crisis, developing sustainable solutions to enhance or replace our current agricultural practices is critical: the agricultural sector exerts important environmental pressure through its aggressive land, water and pesticide usage combined with the ever increasing demand on food supply. Mitigating this problem requires developing more sustainable and efficient agricultural techniques.
We are in the process of creating and growing a team of researchers expert in the field of machine learning and data-mining. Ultimately, our aim is to create solutions to eliminate the need to manually define personalization strategies. We are working with more than 1000 retail locations across North America and collecting large-scale datasets of customer behaviour. Through a data-sharing/consulting partnership we plan to perform research on the design of recommender systems and predictive models customized for the datasets available to retailers.
The multiple sclerosis (MS) clinic at St. Michaelâs Hospital (SMH) is among the largest in the world. While considerable data is collected from the MS clinic in both structured and unstructured form, the ability to glean this information to assess quality of care and conduct advanced analytics such as predictive modeling is limited. In this project, a quality improvement dashboard will be developed based on automation of clinical information extraction process.
SS&C processes more than 80% of financial scanned and faxed documents in the US and requires large amount of manual labor in order to map information from a document into another form. Advances in neural networks applied to computer vision have produced text detection and recognition that nears human performance.