guang

Guangwei Yu

Data scientist at Layer6 AI

guang [at] layer6 [dot] ai

 

Brief Bio

I obtained my Masters of Science in Applied Computing from University of Toronto in 2015. I currently lead the computer vision efforts at Layer6. My interest broadly spans computer vision, recommender systems, and medical image applications.

I enjoy participating in data science competitions. Some highlights:

  • 4th place: RSNA Pneumonia Detection Challenge 2018 hosted by Kaggle and presented at RSNA2018 in Chicago, IL. [site][pdf]
  • 2nd place: Google Landmark Retrieval Challenge 2018 hosted by Kaggle and presented at CVPR2018 workshop in Salt Lake City, UT. [site][pdf]
  • 1st place: 2017 ACM RecSys Challenge hosted by Xing and presented at Recsys 2017 in Como, Italy. [site][pdf]

Papers

Publications:

  • DropoutNet: Addressing Cold Start in Recommender Systems
    Maksims Volkovs, Guang Wei Yu and Tomi Poutanen
    In proceedings of NIPS 2017
    [pdf] [code]
  • Content-based Neighbor Models for Cold Start in Recommender Systems
    Maksims Volkovs, Guang Wei Yu and Tomi Poutanen
    In proceedings of RecSys 2017
    [pdf]
  • Effective Latent Models for Binary Feedback in Recommender Systems
    Maksims Volkovs and Guang Wei Yu
    In proceedings of SIGIR 2015
    [pdf]
Undergraduate Thesis:

  • Characterizing SBP-SAT Operators for CFD Application
    Guang Wei Yu, supervised by D. W. Zingg
    The second-derivative PDEs with variable-coefficient model the full Navier-Stokes equations which are the governing equations in computational fluid dynamics (CFD). Investigation of the accuracy of summation-by-parts operators for second-derivatives with variable-coefficients using numerical simulation found that error reduction of up to 70% can be achieved for this class of problem with optimized parameters.
    [pdf]

Talks

  • Cold Start Recommendations at Scale
    Presented at 2017-2018 Machine Learning Advances and Applications Seminar
    The Fields Institute for Research in Mathematical Sciences
    University of Toronto on November 16, 2017
    [site] [video]

Projects

  • Aircraft Design
    In a team of four, we designed and constructed a radio controlled model aircraft. The aircraft was designed to optimize a cost objective that is a function of flight speed and payload capacity while completing a predetermined flight course. The aircraft constructed was capable of taking off with a total weight of 1.67kg, completing the course and landing successfully.
    [pdf] [video]