Monday, August 14, 2023

Roll up your sleeves and get ready to cut the mustard on campus

An overgrowth of garlic mustard plants with a sign saying "garlic mustard pull"

A message from the Sustainability Office.

On August 17 from 11:00 a.m. to 1:00 p.m., help the Sustainability Office remove invasive garlic mustard to make room for a future pollinator garden. 

We will continue to tackle a dense patch of garlic mustard beside the DWE parking lot.

Volunteers stand with several overstuffed garbage bags containing pulled garlic mustard.

No prior experience is required. Tools, gloves, and light refreshments will be provided. ⁣

Sign up today!

New model reduces bias and enhances trust in AI decision-making and knowledge organization

A robotic hand touches a computer display with an "AI Ethics" icon glowing on it.

University of Waterloo researchers have developed a new explainable artificial intelligence (AI) model to reduce bias and enhance trust and accuracy in machine learning-generated decision-making and knowledge organization.  

Traditional machine learning models often yield biased results, favouring groups with large populations or being influenced by unknown factors, and take extensive effort to identify from instances containing patterns and sub-patterns coming from different classes or primary sources.  

The medical field is one area where there are severe implications for biased machine learning results. Hospital staff and medical professionals rely on datasets containing thousands of medical records and complex computer algorithms to make critical decisions about patient care. Machine learning is used to sort the data, which saves time. However, specific patient groups with rare symptomatic patterns may go undetected, and mislabeled patients and anomalies could impact diagnostic outcomes. This inherent bias and pattern entanglement leads to misdiagnoses and inequitable healthcare outcomes for specific patient groups. 

Thanks to new research led by Dr. Andrew Wong, a distinguished professor emeritus of systems design engineering at Waterloo, an innovative model aims to eliminate these barriers by untangling complex patterns from data to relate them to specific underlying causes unaffected by anomalies and mislabeled instances. It can enhance trust and reliability in Explainable Artificial Intelligence (XAI.) 

“This research represents a significant contribution to the field of XAI,” Wong said. “While analyzing a vast amount of protein binding data from X-ray crystallography, my team revealed the statistics of the physicochemical amino acid interacting patterns which were masked and mixed at the data level due to the entanglement of multiple factors present in the binding environment. That was the first time we showed entangled statistics can be disentangled to give a correct picture of the deep knowledge missed at the data level with scientific evidence.”  

This revelation led Wong and his team to develop the new XAI model called Pattern Discovery and Disentanglement (PDD). 

“With PDD, we aim to bridge the gap between AI technology and human understanding to help enable trustworthy decision-making and unlock deeper knowledge from complex data sources,” said Dr. Peiyuan Zhou, the lead researcher on Wong’s team.  

Professor Annie Lee, a co-author and collaborator from the University of Toronto, specializing in Natural Language Processing, foresees the immense value of PDD contribution to clinical decision-making.   

The PDD model has revolutionized pattern discovery. Various case studies have showcased PDD, demonstrating an ability to predict patients’ medical results based on their clinical records. The PDD system can also discover new and rare patterns in datasets. This allows researchers and practitioners alike to detect mislabels or anomalies in machine learning.  

The result shows that healthcare professionals can make more reliable diagnoses supported by rigorous statistics and explainable patterns for better treatment recommendations for various diseases at different stages. 

The study, Theory and rationale of interpretable all-in-one pattern discovery and disentanglement system, appears in the journal npj Digital Medicine. 

The recent award of an NSER Idea-to-Innovation Grant of $125 K on PDD indicates its industrial recognition. PDD is commercialized via Waterloo Commercialization Office.

R+T Park hosts beer garden and other notes

Pop-Up Beer Garden banner featuring an illustration of a foamy beer mug.

The David Johnston R+T Park will be hosting a charity pop-up beer garden on Wednesday, August 16 in support of Spectrum Waterloo.

The event will be held at 375 Hagey Boulevard from 2:00 p.m. to 5:30 p.m. Block Three Brewing and a food truck will be in attendance.

Information Systems and Technology (IST) has announced that Quest will be down and unavailable on Sunday, August 20 from 6:45 a.m. to 1:00 p.m. as it undergoes scheduled maintenance.

Writing and Communication Centre offices closed today

"Due to ongoing HVAC issues affecting temperatures in the Writing and Communication Centre's offices, the WCC offices and The Write Spot in South Campus Hall will be closed Monday, August 14," says a note from WCC. "All appointments will be moved online, drop-ins will be held virtually, and other programs will be moved or rescheduled. Please visit our website for more information." WCC anticipates that it will be business as usual in their offices beginning Tuesday, August 15.

Link of the day

Where were you when the lights went out? The Northeast Blackout, 20 years later

When and Where 

Waterloo Warriors Youth Camps. Spring and Summer camps available for Boys and Girls ages 5-18. Baseball, Basketball, Football, Volleyball, Hockey and Multi-Sport and Games. Register today.

Student Health Pharmacy in the basement of the Student Life Centre is now offering Covid booster shots (Pfizer and Moderna) and flu shots. Call 519-746-4500 or extension 33784 for an appointment. Walk-ins always welcome.

Final examination period, Friday, August 4 to Saturday, August 19.

Ontario Mennonite Music Camp, Sunday, August 13 to Friday, August 25, Conrad Grebel University College.

Technology Governance Summer School, Monday, August 14 to Friday, August 18, Balsillie School of International Affairs.

Inclusive Research Tools: Identifying and Addressing Barriers, Monday, August 14, 11:00 a.m. to 12 noon. Register now.

Centre for Teaching Excellence New Faculty Teaching Days, Tuesday, August 15 to Friday, August 18. Registration is required

Sustainability Office Garlic Mustard Pull, Thursday, August 17, 11:00 a.m. to 1:00 p.m., DWE parking lot. Sign up today.

Land Skills for Wellness and Sustainability Project: Weaving Together with the Land Nature Walk, Saturday, August 19, 10:00 a.m. to 12 noon.

NEW - Quest down for scheduled maintenance, Sunday, August 20, 6:45 a.m. to 1:00 p.m.

You+Waterloo Optometry Speaker Series featuring Dr. C. Lisa Prokopich, “Dry Eye Management,” August 24, 6:30 p.m., Borealis Grill and Restaurant. RSVP by Friday, August 18.

Celebrating 50 years - Renison Residence Reunion, Friday, August 25 to Sunday, August 27.

Co-operative work term ends, Friday, August 25.

Waterloo Pharmacy Annual Alumni and Friends Golf Invitational + Dinner, Monday, August 28, Grey Silo Golf Course.

International Student Orientation, Thursday, August 31.

Fall first-year Residence Move-In, Thursday, August 31 to Sunday, September 3.

Land Skills for Wellness and Sustainability Project: Connecting to the Land, Thursday, August 31, 5:00 p.m. to 7:00 p.m.

Fall Orientation, Saturday, September 2 to Saturday, September 9.

Labour Day, Monday, September 4, most university operations and buildings closed.

Co-operative work term begins, Tuesday, September 5.

Management Sciences seminar featuring Margot Racat, IDRAC Business School, “Haptics and Need for Touch in Retail Environments: Bringing Back Tangibility to Consumers?” Tuesday, September 5, 11:00 a.m. to 12 noon, CPH 4335.

Lectures and classes begin, Wednesday, September 6.

Music Ensemble Auditions start on Wednesday, September 6. 

When and Where to get support 

Check out the support listings for faculty, staff and students.