Prev:
Q10 Next:
Q12
Back to week 3 page:
Link
# Lecture 11 Examples
📗 My handwriting is really bad, you should copy down your notes from the lecture videos instead of using these.
Lecture 11 Zoom Annotated (2021):
Link
Lecture 11 Pre-recorded Annotated (from 2020, please use with caution):
Link
# Q11 Quiz Instruction
📗 The quizzes must be completed during the lectures. Alternative ways to get the points are listed under "Grading Scheme" on the
index page. No Canvas submissions are required. The grades will be updated at the end of the week on Canvas.
# Game Results
📗 Guess which movie will have the highest box office (July 2021 movies only):
Prior (guess):
Likelihood (which movies are you planning to see):
Posterior (guess again):
Actual (in millions, other = the Boss Baby):
38 students changed their choices.
23,35,8,1,1
24,36,6,1,11
9,32,4,1,3
173,182,67,102,57
Fast 9,Black Widow,Space Jam,Jungle Cruise,Other
# Naive Bayes Demo
📗 Training
Data:
Column separator:
, row separator:
Label column index (first column is 0):
, columns to plot:
Smoothing:
Train
N (number of items):
, M (number of features):
, K (number of classes):
Prior:
, likelihood:
Scatter plot of the data:
Decision boundary: number of squares per row:
Diagram of the classifier:
📗 Validation
K Fold (-1 for Leave-One-Out):
, show error:
Parameter name:
, list of values:
Validate
Training set accuracy:
, 95% confidence:
Validation accuracy:
, average accuracy:
Validation accuracy plot:
ROC and Precision-recall curves:
📗 Testing
Test set:
Or use nested subsets to train:
and the rest to test
Test
Predictions:
, probabilities:
Test set accuracy:
, average accuracy:
Confusion matrix:
Learning curve accuracy plot (for subsets):
Last Updated: November 18, 2024 at 11:43 PM