Fields-CQAM Public Lectures: Ali Ghodsi, University of Waterloo


What is missing from common practice in machine learning?

AI, and machine learning in particular, is enjoying its golden age. Machine learning has changed the face of the world over the past two decades but we are still a long way from achieving a general artificial intelligence. In this talk, I will discuss a couple of elements that I believe are missing from common practice in machine learning, including incorporating causality and creating a new framework for unsupervised learning.


Biography

Ali Ghodsi is a Professor in the Department of Statistics and Actuarial Science at the University of Waterloo. His research involves statistical machine-learning methods. Ghodsi's research spans a variety of areas in computational statistics. He studies theoretical frameworks and develops new machine learning algorithms for analyzing large-scale data sets, with applications to bioinformatics, data mining, pattern recognition, robotics, computer vision, and sequential decision making.

Date:

Thursday, June 20th, 2019.


Presentation

6:00 pm - 7:00 pm.


Networking

7:00 pm - 8:00 pm.


Location

Health Science Building, Rm. 1301 (located on the ground floor), Carleton University.

Free admission for this public lecture:

RSVP onsite.

Friday Workshop Speakers



McGill University

Benjamin C. M. Fung

Keynote Presentation: Data Mining and Machine Learning for Authorship and Malware Analyses



National Research Council

Isar Nejadgholi

Privacy-preserving data augmentation in medical text analysis



MindBridge Ai

Robin Grosset

Class Imbalance in Fraud Detection



IMRSV Data Labs

Isuru Gunasekara

Handling class imbalance in natural language processing



University of Ottawa

Herna L. Viktor

Adaptive learning with class imbalanced streams



McGill University

Hamidreza Sadreazami

Radar-based fall monitoring using deep learning



Interset

Shaun Pilkington

Cybersecurity: Top 5 class imbalance ML challenges and data sets



Lemay.ai

Daniel Shapiro

AuditMap.ai: Hierarchical Sentence Classification in Unstructured Audit Reports



RANK Software Inc.

Dušan Sovilj

Deep Learning techniques for unsupervised anomaly detection



Friday Workshop

Date:

Friday, June 21st, 2019.


Time:

8:30 am - 4:30 pm.


Location:

Residence Commons, Carleton University.


Early registration has closed. Please register onsite for this workshop; lunch is not covered for onsite registrants.

Time Title Speaker Affiliation
8:30 am - 9:00 am Registration
9:00 am - 9:15 am Opening Remarks
9:15 am - 10:00 am Keynote Presentation:

Data Mining and Machine Learning for Authorship and Malware Analyses
Abstract
Slides
Benjamin C. M. Fung
Biography
McGill University
10:00 am - 10:30 am Break
10:30 am - 11:45 am Privacy-preserving data augmentation in medical text analysis
Abstract
Slides
Isar Nejadgholi
Biography
National Research Council
Class Imbalance in Fraud Detection
Abstract
Robin Grosset
Biography
MindBridge Ai
Handling class imbalance in natural language processing
Abstract
Slides
Isuru Gunasekara
Biography
IMRSV Data Labs
11:45 am - 12:45 pm Lunch
12:45 pm - 2:00 pm Adaptive learning with class imbalanced streams
Abstract
Herna L. Viktor
Biography
University of Ottawa
Radar-based fall monitoring using deep learning
Abstract
Hamidreza Sadreazami
Biography
McGill University
Failure modelling of a propulsion subsystem: unsupervised and semi-supervised approaches to anomaly detection
Abstract
Julio J. Valdés
Biography
National Research Council
2:00 pm - 2:15 pm Break
2:15 pm - 3:30 pm Cybersecurity: Top 5 class imbalance ML challenges and data sets
Abstract
Shaun Pilkington
Biography
Interset
AuditMap.ai: Hierarchical Sentence Classification in Unstructured Audit Reports
Abstract
Daniel Shapiro
Biography
Lemay.ai
Deep Learning techniques for unsupervised anomaly detection
Abstract
Dušan Sovilj
Biography
RANK Software Inc.
3:30 pm - 3:45 pm Closing Remarks

Directions


The Carleton University interactive campus map is available here.



Parking

There is pay & display parking at P18; please see the Carleton University parking map here.



Health Science Building

The health science building is a new building. It is building number 49 on this map. The nearest parking facilities are P16 and P9 (see the parking map).



Residence Commons

The Residence Commons building is labelled "CO" on the Carleton University interactive campus map.



Our Sponsors


About Us

Fields-CQAM: Carleton Lab

The Centre for Quantitative Analysis and Modelling at the Fields Institute fund research related to mathematical sciences throughout Canada. Its Carleton University branch (Fields-CQAM: Carleton Lab) is supervised by professors Shirley Mills, James Green, and Sreeraman Rajan. Our research interests include the detection, computation, and forecasting of rare or anomalous events. We are also keen on improving machine learning algorithms under the prescence of class imbalanced datasets.



Workshop Organization Committee

Shirley Mills (top-left), James Green (top-right), Sreeraman Rajan (bottom-left), Roy Chih Chung Wang (bottom-right).