CSE 163
ML and Images
��Hunter Schafer
Questions During Class? Ask in Zoom chat!
💬Before Class: Favorite board/card game?
Machine Learning
Terms from machine learning
2
ML + Images
How do we do machine learning on images?
3
10 | 20 | 30 |
40 | 50 | 60 |
70 | 80 | 90 |
10 |
20 |
30 |
40 |
50 |
60 |
70 |
80 |
90 |
Raw Image
Unrolled Image
ML + Images
Pros: Simple transformation (just a call to reshape!)
Cons: It loses the idea of “neighboring” pixels (up/down)
4
Despite these drawbacks, it can work in practice on some problems!
Neural Network
Based on how our brains �work
5
Example
What is the output for this neuron if the inputs are 0 for the first input and 1 for the second. The activation function is the step function (0 if negative, 1 otherwise). The bias should be subtracted from the weighted sum before applying the activation function.
6
3
-2
4
Unsupervised
Learning
So far, we have seen supervised machine learning, where we have to explicitly shown the algorithm the labels
Unsupervised machine learning lets the algorithm try to learn trends on its own without providing explicit labels
Examples
7
Group Work:
Best Practices
When you first working with this group:
Tips:
8