CSE 163

ML and Images�

Suh Young Choi�

🎶 Listening to: Unwed Sailor

💬 Before Class: You can instantly become fluent in any language, but you’re banned from traveling anywhere that uses it as an official language. What language do you pick?

Announcements

CP 3 and LR 6 due Monday 8/11

​

Project Report/Code due Thursday 8/14

• Turned in via Gradescope
• No late work accepted, no resubmissions

​

Two more resubmission periods remaining, unless…

• If 60% of the class fills out the final course eval (releasing 8/13), then you get a third!
• You may submit any one THA during this “bonus” period (8/20 – 8/22)

​

​

2

This Time

• Machine learning with images

Last Time

• Convolutions
• Kernel operations

3

Machine Learning, revisited

Terms from machine learning

• Features / labels
• Learning algorithm
• Model
• Model class
• Training set / test set
• Parameters / Hyperparameters

4

ML + Images

How do we do machine learning on images?

• Simplest: Unroll the image into a vector
• Complex: Use other tools to extract features from the images

​

​

5

Raw Image

Unrolled Image

ML + Images

Pros: Simple transformation (just a call to reshape!)

Cons: It loses the idea of “neighboring” pixels (up/down)

• Most machine learning models don’t take position of the features into account
• This is where more complex models like convolutional neural networks come in to encode that local information as features

​

​

6

Despite these drawbacks, it can work in practice on some problems!

​

Neural Network

Based on how our brains �work

7

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.

8

3

-2

4

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.

9

3

-2

4

0

1

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.

10

3

-2

4

0

1

0 * 3 + 1 *(-2) - 4 = -6

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.

11

3

-2

4

0

1

0 * 3 + 1 *(-2) - 4 = -6

squish(-6) = 0

Image Classification

12

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

• Clustering
• Outlier detection

13

Project Deliverable Details

Visualizations MUST include:

• Title
• Axis labels
• Legend
• Caption (with figure number)

​

Include in any captions:

• Figure number
• Type of plot
• Variables being plotted
• (Optionally) trends/takeaways from the plot

​

14

Project Deliverable Details

Fig 1. A line plot showing the relationship between shark ages in months and caudal fin lengths in inches.

Project Deliverable Details

Don’t let numbers float (ha) in the vacuum!

• Accuracy / MSE – what do these numbers mean for your ML model?
• Pearson’s R or R-squared values – what does this imply about the strength or direction of the relationship between variables?
• p-values – do you reject or fail to reject your null hypothesis? What does this imply about your results?
• Percentages, counts, averages, sums, etc:

​

16

Project Deliverable Details

Length requirements

• 15 pages for the report (excluding optional title page and appendix)
• 3 minutes for the video
• Please don’t do this:

​

17

Before Next Time

• Complete Lesson 21
• Remember not for points, but do go towards Checkpoint Tokens
• CP 3 + LR 6 due on Monday

Next Time

• Ethics and Data Science

​

18