Hi all,
Lecture 4: Learning <https://cs50.harvard.edu/summer/ai/2020/lectures/4/> is
now available on the course website. In this part of the course, we
introduce the domain of machine learning, looking at techniques that allow
our AI to learn how to perform a task, without explicit instructions for
how to do so. This week, we'll introduce three broad categories of machine
learning: supervised learning, reinforcement learning, and unsupervised
learning.
In the first part of this project, you'll build a classifier to predict
user behavior on an online shopping website, taking advantage of supervised
learning techniques in scikit-learn <https://scikit-learn.org/>. In the
second part of the project, you'll use reinforcement learning to design an
AI to teach itself how to win at Nim <https://en.wikipedia.org/wiki/Nim>:
through repeatedly playing games against itself, the AI will over time
learn which moves are better than others.
A few other important announcements for this week:
- Quiz 4 <https://cs50.harvard.edu/summer/ai/2020/quizzes/4/> is now
available and is due by 11:59pm ET on Wed 7/22. As a reminder, each quiz is
open-book: you may use any and all non-human resources during a quiz, but
the only humans to whom you may turn for help or from whom you may receive
help are the course’s heads. And remember to submit your quiz via
Gradescope as well!
- Project 4 <https://cs50.harvard.edu/summer/ai/2020/projects/4/> is now
available as well and is due by 11:59pm ET on Sun 7/26.
- Sections <https://cs50.harvard.edu/summer/ai/2020/sections/> this week
will be an opportunity to talk more about machine learning. You're
encouraged to attend if you can!
As always, feel free to reach out to me or any of the course staff with any
questions!
All the best,
Brian
Show replies by date