6. Supervised Machine Learning
Supervised learning trains with labelled data (think flashcards) to
make predictions on new data
Labelled data - This has a label attached that tells you what the
data is.
There are two main categories of supervised learning:
• Regression- output will be Numerical , Decimal value
• Classification – output will be categorical value like ‘dog or not
dog’.
7. Un-Supervised Machine Learning
Unsupervised learning explores unlabelled data, finding hidden
patterns and groups
Unlabelled data - This is raw data without any labels.
There are three main categories of supervised learning:
• Clustering: This groups similar data points together, like sorting
customers by purchase history.
• Association rule learning: This finds relationships between data points
• Dimensionality reduction: This simplifies complex data by reducing the
number of features, making it easier to analyse.
9. Simple Linear Regression
(supervised ML)
Goal – To create a best fit
line in such a way that the
summation of the error will
be minimum.
Prediction Formula
y_pred = mx + c
13. What we will Learn today :-
• Convergence Algorithm
• Multiple Linear Regression
• Types of Cost/Loss Function
14. Convergence Algorithm
Convergence in machine learning is when a model's performance
stops improving during training, signifying it has reached an
optimal state.
15.
16.
17. Multiple Linear Regression
Multiple linear regression predicts a value using several
factors. Imagine estimating house prices based on size,
location, and number of bedrooms.
So our equation will be :-
Y_pred = c + m1x1 + m2x2 + m3x3 +
…….+mnxn