Griffin AI Day 1 - TheEvergreenStateCollege/upper-division-cs-23-24 GitHub Wiki
AI Day 1
Draw a hand-drawn digit in the first demo box and click "check digit".
Click on several of the input nodes (in the first layer) and see a corresponding pixel light up yellow on your input hand-drawn digit.
If you had to guess, describe in English one possible connection between nodes and pixels.
Each node in the first layer represents a pixel. I.e. the value of the node is determined by the light level of the pixel.
Click on several of the hidden nodes (in the second layer) and see two images pop up, one with all red/blue pixels, and one masked to just your hand-written digit.
If you had to guess, describe in English what the two images might mean.
The image on the left shows activation values. The image on the left shows the 2 I drew, overlayed over the activation values.
See the incoming edges light up between your selected nodes and the input nodes in the first layer.
What does a bright blue edge mean in terms of the numerical weight on that edge? Is it less than zero, greater than zero, or equal to zero?
greater than zero
What does a bright red edge mean in terms of the numerical weight on that edge? Is it less than zero, greater than zero, or equal to zero?
less than zero
Answer the above questions for a slightly blue or slightly red edge.
only slightly, or slightly less
Click on your hand-drawn digit to reset the demo, and draw a new digit.
Click on some hidden nodes (in the second layer). Do you think the color (weight) of these edges are the same as from your previous hand-drawn digit?
I'm not sure what this is asking, so I'll come back.
Reset the demo and draw another hand-drawn digit to test your theory.
Whether it's the same or different, describe in English why this is the case.
Conceptually, what would the author of this website have to do
It looks like the image on the left side doesn't change either time, so I'm guessing it's not changing, or only changing slightly. The image on the right however is the one I draw, and each drawing overlays differently over the image on the left.
Reset the demo and draw a digit to be as ambiguous as possible (for example, halfway between a 4 and a 9).
Run the network forward to check the digit. See if you can get a halfway gray color between two or more output nodes (in the last layer), indicating equal (un)certainty.
What would you do in this case, if you needed this network to classify the digit definitely? (e.g. if you work for the U.S. Postal Service)
A machine learning model is trained from data, like a binary executable file is compiled from source files.
In what ways could this be a valid analogy? Consider this prediction:
if i give you a binary executable program which doesn't need the internet to run (for example, a tic-tac-toe game), and you airgap yourself from the internet, do you have everything you need to run the game?
if I give you an ML model and all input images that I need to have classified on the same computer, and you airgap yourself from the internet, do you have everything you need to classify the input images?
Name some differences in this analogy; that is, how is an ML model trained from data different than a compiled binary file?
- a machine learning program is like an extension of an executable because it is an executable, but the program takes time to learn.