machine learning for non-technical people
TRANSCRIPT
![Page 1: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/1.jpg)
Machine Learning for Non-technical
People
Slater Victoroff
![Page 2: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/2.jpg)
Designed by freepik.com
YOU!
The non-technical audience interested
in Learning about
Machine Learning!
Who is this talk for?
![Page 3: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/3.jpg)
Who am I?• Slater Victoroff
• Olin College of Engineering
• Typical young hoodie, flip-flop wearing entrepreneur
• Someone who cares very deeply about machine learning
• CEO of indico
![Page 4: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/4.jpg)
What is Machine Learning?
![Page 5: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/5.jpg)
Such a big buzzword.
Here’s what it comes down to in a human definition:
A class of computer algorithms and mathematical models that allow machines to perform general tasks, like identifying human faces in photos. The models are used to make predictions and decisions, which you can then use to solve real world problems, such as understanding how your customers feel about your brand across various social media channels. The neat thing is that instead of hiring 100 people to analyze 1,000 data points each, you could get a single machine to do it in a fraction of the time.
![Page 6: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/6.jpg)
Quick Poll
Can you use machine learning in the following industries?
![Page 7: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/7.jpg)
Factories
![Page 8: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/8.jpg)
![Page 9: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/9.jpg)
Smart Phones
![Page 10: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/10.jpg)
Robots
![Page 11: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/11.jpg)
Human Robots
![Page 12: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/12.jpg)
NOT HUMAN ROBOTS
![Page 13: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/13.jpg)
Machine Learning is Blurry
![Page 14: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/14.jpg)
Language is blurry — sarcasm, etc.Where there’s a gray area,
machine learning can solve the issue.
Computers are bad at the world when there is inconsistency.
![Page 15: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/15.jpg)
Say you’re a brand and you want to know what people are saying about your brand.
You look through everyone talking about your brand on Twitter, Facebook, etc..
Now you want to look at how popular those people are to find your influencers.
And finally, you want to know… what are they talking about?
In the old spreadsheet way, we have always just ignored these problems as they were in a gray area we couldn’t
access.
A social media example
![Page 16: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/16.jpg)
Machine learning is
born in very ordinary
circumstances
![Page 17: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/17.jpg)
![Page 18: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/18.jpg)
• Marty McFly ended up in 1955 which is the same year that the first branch of ML came out (AI movie to come later)
• Georgetown and IBM Cold War found ML to be useful as they wanted to translate a large amount of Russian text to analyze
• MIT went after the image side, teaching computers to recognize objects and scenes. They tried to teach the computer to look at a picture and determine a bird or a plant.
![Page 19: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/19.jpg)
Machine Translation will be a Solved
Problem in Three to Five Years
- Optimistic Researcher 1954
![Page 20: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/20.jpg)
CSAIL• The Computer Science and Artificial
Intelligence Laboratory – known as CSAIL is the largest research laboratory at MIT and one of the world’s most important centers of information technology research.
• Founded in the 1940’s by Marvin Minsky
![Page 21: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/21.jpg)
![Page 22: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/22.jpg)
We’re pretty sure we bit off more than we
can chew here- ALPAC 1966
![Page 23: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/23.jpg)
• Committees were spun up to precise translation and recognition.
• In one solid decade, we effectively made no progress. We had one-off ML systems.
• We could teach a computer to understand one sentence by showing it that one sentence.
• We made no progress, spent a lot of money, and cut the research. It was the death of an era.
During that time…
![Page 24: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/24.jpg)
Time Passes
![Page 25: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/25.jpg)
Arnold brings us back!
![Page 26: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/26.jpg)
Machine Learning Goes Mainstream
![Page 27: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/27.jpg)
Thumbs up? Sentiment classification
usingmachine learning
techniques.Bo Pang, Lillian Lee, and Shivakumar
Vaithyanathan.
![Page 28: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/28.jpg)
Sentiment analysis = determine if a piece of text is positive or negative.
How do we do it? Well, we map each word to its sentiment and give the words a score.
AKA: A Lexicon-based approach
Sentiment Analysis
![Page 29: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/29.jpg)
Word Positivity
Great 0.9
Terrible 0.1
Alright 0.6
Mediocre 0.4
![Page 30: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/30.jpg)
This sandwich isn’t bad
![Page 31: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/31.jpg)
Words Positivity
Isn’t bad 0.6
Isn’t good 0.3
Ain’t half-bad 0.73
Above average 0.7
![Page 32: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/32.jpg)
“I have to say, that while most of my experiences at tourists traps have been horrendous,
the one I recently went to broke the pattern.”
• Many humans can’t figure out the sentiment of this sentence
• Gray areas of language = why sentiment analysis is quite a difficult problem for computers to solve
![Page 33: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/33.jpg)
How do we know how well we’re doing?
![Page 34: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/34.jpg)
How do we know how good AI is?
![Page 35: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/35.jpg)
• Well, it’s hard• Take a spreadsheet• Label each piece of text for positive vs. negative• Guess which words made it positive or negative• Train the model on half of the spreadsheet and
then make predictions on the other half
Then what.
![Page 36: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/36.jpg)
Train
Test
![Page 37: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/37.jpg)
Still, it’s not that simple
Performance metrics
Overfitting
![Page 38: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/38.jpg)
Customer Did they buy?1 No2 No3 No4 No5 No6 Yes7 No8 No9 No
10 No11 No12 Yes13 No14 No
Performance Metrics
![Page 39: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/39.jpg)
- Accuracy isn’t necessarily the best performance metric
- Predicting sentiment is a very different problem depending on whether the text you’re making predictions on consists of Amazon reviews, tweets, or medical journals
- It also depends on how much data you’ve got
- When you teach a computer what sentiment is, you end up showing it a huge number of examples. Depending on the data you’ve got, the number of examples you might use range from a few hundred to hundreds of millions
- It’s not fair to use those examples to check your model’s accuracy — you already know the answers
Performance Metrics
![Page 40: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/40.jpg)
Learn more about sentiment analysis and performance metrics:
What Even Is Sentiment Analysis?
![Page 41: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/41.jpg)
Precision: fraction of retrieved instances that are relevant
Recall: fraction of relevant instances that are retrieved
Precision vs Recall
![Page 42: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/42.jpg)
OverfittingThis product left me with a deep feeling of regret.
This film left me with a deep feeling of regret, love, and hopelessness for a life not lived.
I #love these new @nike shoes
![Page 43: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/43.jpg)
Overfitting• Overfitting means you “fail to generalise to examples
outside of your training set”• In other words…you’re living under a rock. You’re
great at recognizing everything under your rock, but you don’t understand the rest of the world
• Domain is a factor — there are so many different kinds of text (scientific journal articles vs. tweets)• No one model is going to be the best at every kind of
text
![Page 44: Machine Learning for Non-technical People](https://reader031.vdocuments.site/reader031/viewer/2022030304/587853d61a28ab68198b6d2b/html5/thumbnails/44.jpg)
KNOWLEDGE = POWEREmail us: [email protected]