CPSC 330 Lecture 19: Introduction to deep learning and computer vision

Andrew Roth

Announcements

  • HW7 due date extended to Wednesday
    • Late tokens until Friday
  • HW8 has been released due April 7th
    • If you already started please check the github again as a new question was added!
  • HW9 has been scrapped
    • Course policy is still to drop lowest HW grade
  • Midterm 2 grading is in progress

iClicker 19.0

iClicker cloud join link: https://join.iclicker.com/HTRZ

Select all of the following statements which are TRUE for you.

    1. I found the multiple-choice questions challenging.
    1. The coding questions took a lot of time.
    1. I didn’t like the format of the midterm.
    1. I appreciated the mix of coding, conceptual, and multiple-choice questions.
    1. I felt the midterm was a good reflection of what we cover in the lectures and homework assignments.

iClicker 19.1

iClicker cloud join link: https://join.iclicker.com/HTRZ

Select all of the following statements which are TRUE.

    1. It’s possible to use word2vec embedding representations for text classification instead of bag-of-words representation.
    1. The topic model approach we used in the last lecture, Latent Dirichlet Allocation (LDA), is an unsupervised approach.
    1. In an LDA topic model, the same word can be associated with two different topics with high probability.
    1. In an LDA topic model, a document is a mixture of multiple topics.
    1. If I train a topic model on a large collection of news articles with K = 10, I would get 10 topic labels (e.g., sports, culture, politics, finance) as output.

Class notebook