Events

Filter by:

Limit to events where the first date of the event:
Date range
Limit to events where the first date of the event:
Limit to events where the title matches:
Limit to events where the type is one or more of:
Limit to events tagged with one or more of:
Limit to events where the audience is one or more of:
Wednesday, July 17, 2019 2:00 pm - 2:00 pm EDT (GMT -04:00)

PhD Seminar: Comparing EM with GD in Mixture Models of Two Components

Guojun Zhang, PhD candidate
David R. Cheriton School of Computer Science

The expectation-maximization (EM) algorithm has been widely used in minimizing the negative log likelihood (also known as cross entropy) of mixture models. However, little is understood about the goodness of the fixed points it converges to. 

Thursday, July 18, 2019 1:30 pm - 1:30 pm EDT (GMT -04:00)

PhD Seminar: Attention Mechanisms for Weakly Supervised Image Segmentation

Paulo Pacheco, PhD candidate
David R. Cheriton School of Computer Science

In this seminar I will discuss some of the current state-of-the-art methods for generating attention maps in weakly supervised (image level annotations) for classification tasks, aiming image segmentation inference and object localization.

Matthew Angus, Master’s candidate
David R. Cheriton School of Computer Science

There exists wide research surrounding the detection of out of distribution sample for image classification. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual objects causing an image to be out of distribution. 

Rahul Iyer, Master’s candidate
David R. Cheriton School of Computer Science

Social interactions in the form of discussion are an indispensable part of collaborative software development. The discussions are essential for developers to share their views and to form a strong relationship with other teammates. These discussions invoke both positive and negative emotions such as joy, love, aggression, and disgust. Additionally, developers also exhibit hidden behaviors that dictate their personality. Some developers can be supportive and open to new ideas, whereas others can be conservative. Past research has shown that the personality of the developers has a significant role in determining the success of the task they collaboratively perform.

Jonathan Vi Perrie, Master’s candidate
David R. Cheriton School of Computer Science

Over the years, hit song science has been a controversial topic within music information retrieval (MIR). Researchers have debated whether an unbiased dataset can be constructed and what it means to successfully model song performance. Often classes for modelling are derived from one component of song performance, like for example, a song's peak position on some chart. 

Alexander Sachs, Master’s candidate
David R. Cheriton School of Computer Science

GitHub is an excellent democratic source of software. Unlike traditional work groups however, GitHub repositories are primarily anonymous and virtual. Traditional strategies for improving the productivity of a work group often include external consultation agencies that do in-person interviews. The resulting data from these interviews are then reviewed and their recommendations provided. In the online world however, where colleagues are often anonymous and geographically dispersed, it is often impossible to apply such approaches.

Friday, August 16, 2019 2:30 pm - 2:30 pm EDT (GMT -04:00)

Master’s Thesis Presentation: Policy Extraction via Online Q-Value Distillation

Aman Jhunjhunwala, Master’s candidate
David R. Cheriton School of Computer Science

Recently, deep neural networks have been capable of solving complex control tasks in certain challenging environments. However, these deep learning policies continue to be hard to interpret, explain and verify, which limits their practical applicability. Decision Trees lend themselves well to explanation and verification tools but are not easy to train especially in an online fashion. The aim of this thesis is to explore online tree construction algorithms and demonstrate the technique and effectiveness of distilling reinforcement learning policies into a Bayesian tree structure.

Hamidreza Shahidi, Master’s candidate
David R. Cheriton School of Computer Science

A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several natural language processing (NLP) tasks. 

Friday, September 6, 2019 10:00 am - 10:00 am EDT (GMT -04:00)

PhD Seminar: Biochemistry Procedure-Oriented Ontology: A Case Study

Mohammed Alliheedi, PhD candidate
David R. Cheriton School of Computer Science

Ontologies must provide the entities, concepts, and relations required by the domain being represented. The domain of interest in this paper is the biochemistry experimental procedure. The ontology language being used is OWL-DL. OWL-DL was adopted due to its well-balanced flexibility among expressiveness (e.g., class description, cardinality restriction, etc.), completeness, and decidability. These procedures are composed of procedure steps, which can be represented as sequences. Sequences are composed of totally ordered, partially ordered, and alternative subsequences. 

Jian Deng, Master’s candidate
David R. Cheriton School of Computer Science

This thesis presents Multi-view Labelling Object Detector (MLOD). The detector takes an RGB image and a LIDAR point cloud as input and follows the two-stage object detection framework \cite{girshick2015fast} \cite{ren2015faster}. A Region Proposal Network (RPN) generates 3D proposals in a Bird's Eye View (BEV) projection of the point cloud. The second stage projects the 3D proposal bounding boxes to the image and BEV feature maps and sends the corresponding map crops to a detection header for classification and bounding-box regression.