# Q19 Quiz Instruction
📗 The quizzes must be completed during the lectures. No Canvas submissions are required. The grades will be updated by the end of the week on Canvas. Alternative ways to get the points are listed below in the D19 sections.
📗 Please submit a regrade request if (i) you missed a few questions because you are late or have to leave during the lecture; (ii) you selected obviously incorrect answers by mistake (one or two of these shouldn't affect your grade):
Link
Answer |
Points |
Out of |
Correct |
1 |
Number of Questions |
Plausible but Incorrect |
1 |
- |
Obviously Incorrect |
0 |
- |
# D5 Sharing Solutions on Piazza
📗 Use the sign-up sheet:
Google Sheet. You can sign up and post anonymously (anonymous Piazza posts are not anonymous to instructors).
Requirement |
M Questions |
Past Exam Questions |
List of Questions |
M9-10Q1-10 |
X4Q1-5 |
Due Date |
Aug 8 |
|
Name of Post |
M?Q? |
X?Q? |
Piazza Tag |
one of m9-10 or d5 |
one of m9-10 or d5 |
Type of Post |
public Piazza note |
same |
Include |
(1) Screenshot of the question |
same |
- |
(2) Detailed step-by-step solution |
same |
- |
(3) Brief explanation of each step |
same |
If your post satisfies the requirements (1), (2), (3), one of the course staff will "like" your post and you will receive 0.5 points for the post.
The past exams can be found on pages
X1,
X2,
X3,
X4,
X5,
# D5 Discussion Topic
📗 Please create a follow-up discussion post on the Piazza (it is okay to post anonymously). No Canvas submissions are required. The grades will be updated at the end of the week on Canvas.
Requirement |
Discussion |
- |
Topic |
see below |
- |
Due Date |
Aug 8 |
- |
Type of Post |
Piazza follow-up |
- |
Include |
(1) Image or screenshot |
- |
- |
(2) Brief discussion or explanation |
(one or two sentences) |
If your post satsifies the requirements (1), (2), you will receive 0.5 points for the post.
📗 Go the genetic algorithm demo
self-driving car demo. Play with the network size parameters and the genetic algorithm parameters to see how they affect how fast the cars learn to drive. Wait for a few generations until most of the cars can complete a whole lap successfully and take a screenshot. Share the screenshot on Piazza and briefly discuss what you find (which parameter you changed, what it does, and how it may affect learning).
📗 If you are familiar with JavaScript, you can play with the code for activation function, mutation, crossing, and selection too.
Image from
Google's self-driving car project via
Techcrunch.