[go: up one dir, main page]
Scribd
Upload
12 views11 pages

Intro To Machine Learning

The document is an introduction to machine learning presented by Sumedh Garimella, a data scientist at Capgemini. It covers key concepts such as supervised and unsupervised learning, classification and regression, along with their respective metrics. The presentation also includes exercises and a Q&A session.

Uploaded by

ncl9100
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
12 views11 pages

Intro To Machine Learning

The document is an introduction to machine learning presented by Sumedh Garimella, a data scientist at Capgemini. It covers key concepts such as supervised and unsupervised learning, classification and regression, along with their respective metrics. The presentation also includes exercises and a Q&A session.

Uploaded by

ncl9100
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

Intro to Machine Learning

Data Science Club NYU

Sumedh Garimella, November 6, 2024


About Me
Sumedh Garimella

• Data Scientist at Capgemini


• Python, Azure, GenAI
• Georgia Tech
• BS CS ’22, MS CS ‘23

• Previous experience
• Interned at Coca-Cola, Bank of America, NCR

• Hobbies
• EDM Producer, DJ
• Cooking
What is Machine Learning?

• subset of Arti cial Intelligence


• allowing computers to learn from data and
modeling as opposed to being hard-coded

• Supervised vs Unsupervised Learning


• Unsupervised: let the computer form its own
understanding from unlabeled data

• Supervised: provide labeled training data to


model impact on target variable(s).
fi
Classi cation

• Prediction of discrete values


• Use Cases:
• Spam vs non-spam
• Positive vs negative for
diseases

• Genre classi cation


• Churn prediction
fi
fi
Classi cation Metrics

• Precision
• What % of true predictions are actually
true?

• Recall
• What % of actual trues are recognized?
• F1 score
• Harmonic mean of precision and recall
• Cross-Entropy
• Di erence between predicted and actual
values
ff
fi
Regression

• Prediction of continuous values


• Use Cases:
• Stock price forecasting
• Score predictions
• Infectious disease tracking
• Public sentiment analysis
Regression Metrics

• Mean Absolute Error (MAE)


• Punishes all error proportional to the
size of error

• Mean Squared Error (MSE)


• Punishes larger errors more
• R^2 Score
• Measures t of regression model to data
• Root Mean Squared Error (RMSE)
• Normalized version of MSE
fi
Correlation

• The factor by which an


independent variable is related to
a dependent variable

• i.e. how much of a predictor is


variable A for target variable X

• Pearson’s Correlation
Coe cient (PCC)
ffi
Exercises and Live Coding
Q&A
Thank you!

You might also like