Material for Week 2 #15
Conversation
02_ml_models/README.md
Outdated
| 2. Read Andrey Kurenkov's ['Brief' History of Neural Nets and Deep Learning](http://www.andreykurenkov.com/writing/a-brief-history-of-neural-nets-and-deep-learning/) | ||
| 3. Read [ImageNet: The Data That Transformed AI Research—and Possibly the World](https://qz.com/1034972/the-data-that-changed-the-direction-of-ai-research-and-possibly-the-world/) by Dave Gershgorn (Note: Fei-Fei Li is no longer at Google; she is currently Co-Director of the Stanford Human-Centered AI Institute) | ||
| 4. Explore [ImageNet](http://image-net.org/index) | ||
| 5. TBA (exercise related to running ml5 image webcam example and/or teachable machine training -- no code writing just yet.) |
There was a problem hiding this comment.
If the goal is for students to start coding after Session 2 this week, then what will best prepare students? Does it make sense / is there enough time on Monday to open up the p5 editor together, run one of the classification examples, go thru the code line by line (also thinking about Objectives 5 and 6 here), and use this in-class event to prompt the short (but no-coding) exercise(s) to complete before Wednesday?
...and why not both exercises?! An exercise to learn more about MobileNet: for example, how many items does it correctly identify in your home / dorm? If it recognizes a banana, does the banana always have to be in the same position and with the same lighting?
And another exercise to preview Session 2 and get creative with teachable machine inputs and outputs.
There was a problem hiding this comment.
We should also note making sure people can run a local web server?
There was a problem hiding this comment.
I'm also happy to run a session on Friday or another time this week similar to the sessions that the residents do for the comm labs for the first year ITP students if that would be helpful for getting students up and running on any of the technical assignments (rather than just open office hours).
There was a problem hiding this comment.
@ellennickles yes, my plan is to spend probably half the class writing the code for basic image classification from scratch reviewing p5 at the same time. I think I will leave teachable machine and transfer learning for Wednesday to not overload the students and have them do a short blog post and exercise before Wednesday.
@joeyklee For now I am going to stick to the web editor entirely. But yes, this will inevitably come up and I'll need to address in class or through a separate help session. I also have this playlist which covers most of it and hasn't gone too out of date yet?
@lydiajessup That would be amazing! Feel free to just go ahead and schedule something / announce through the class google group!
One README for each week makes sense since each week has a theme. It's helpful to see all the resources in one place.
Monday to Wednesday is such a quick turnaround. In creative computing, students were assigned two blog posts a week: one in which to respond to readings (assigned during session 1) and another for their technical assignments (assigned during session 2). Both were due the night before the first session of the following week. But this is a new class, and maybe this week is different from all the others! If everyone were to write up a short blog post with observations from their ml5 example / teachable machine exercise and post for Wednesday, then that could be a useful way to start the discussion in Session 2. Just saw this on the course overview README: "Responses to reading and other written assignments are also due in class one week after they are assigned and must also be submitted via the class website. Written assignments are expected to be 200 to 500 words in length unless otherwise specified. Grading will follow the same guidelines as above; on time and meeting the criteria specified will be marked as complete. Late (up to 1 week) or partially completed work will be given half credit. Work that is more than a week late, not turned in, or fails to meet the criteria specified will be given no credit." |
|
Thanks @ellennickles I'll update the course README to reflect that smaller exercises are sometimes due between Monday and Wednesday sessions. |
|
While not everything is perfectly resolved, I'm going to go ahead and merge this. Please file any additional issues / pull requests as you see fit. I'll make more updates tomorrow morning before class. |
This is the start of week 2 copy/pasting the material from the Google Doc. Things to add / consider:
READMEfor the full week or two? At the moment I am starting with one.I'll be working on this more over the weekend and finalizing Monday morning.