Week 2: Supervised Learning
Announcements
-
Class participation, EdSTEM and Google Folder.
Tuesday
Recap Notes last week
-
Highlight the patterns your recognized
-
Hands-on in-class exercises
-
Revisit Lab 1 requirements
Pattern Recognition
Narrow down to course introduction, Identify Patterns.
-
Textbooks
-
Topics
-
Weeks
-
Resources
Let’s look at course examples.
Textbooks
All textbooks are free available online, and are optinal, not required.
-
Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
-
2016, Cited by 42286
-
A Course in Machine Learning by Hal Daume III
-
1997, Cited by 33979
In-class exercises:
*Explain to your classmates what you find interesting from one of the textbook *Explain to your classmates your experience with Google Scholar *Explain to your classmates one interesting resource you saw in the Resources from the courses.
Supervised learning
-
5 Machine Learning Basics
-
5.7. supervised, PDF page number 137
-
5.8, unsupervised
-
15, unsupervised learning
In-class exercises:
*Explain to your classmates what is supervised learning *Explain to your classmates what is unsupervised learning
Lab 02
-
Supervised learning Basics
Thursday
Videos (long, hours)
-
Stanford, Andrew Ng, and slides.
-
CMU, Tom Mitchell, both videos and slides.
Videos (short, minutes)
In-class exercises:
*Explain to your classmates what is an interesting topic your saw from these videos.
AAAI Accepted Posters (2022)
AAAI Accepted Posters (2021)
-
AAAI-21 Student Papers and Demonstrations
-
High School
AAAI Accepted Posters (2020)
-
Pattern Recognition from Accepted Posters
-
Practice: Three minutes per poster, all forty posters together, around two hours.
-
AAAI-20 Student Papers and Demonstrations
-
High School
Supervised vs Unsupervised
-
The main difference between supervised and unsupervised learning: Labeled data
Datasets
-
Popular datasets, UCI Datasets
-
Other institutions also use these datasets.
-
sklearn datasets examples
Iris Dataset
-
Programming Competitions use it as well, such as Kaggle.
-
Videos, such as Classification with Iris Dataset.