Scribd
Upload
280 views66 pages

MLT Notes

aktu machine learning techniques

Uploaded by

Aryan Raj
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
280 views66 pages

MLT Notes

aktu machine learning techniques

Uploaded by

Aryan Raj
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/ 66

n

Artificial Neural Network


Decision Boundary

Margin

Support Vector

Supervised learning

Linearly seprabl data


Agent

State

Environment

Reward/penalty system

Action
Size Price Mean(x Mean(Y Devia- Square
Devia-
Product
Sum of
) ) tion (x) tion (y)
devia-
of
tion
devia-
tion for
X
8 10 10 13 -2 -3 6 12 4
10 13 0 0 0 0
12 16 2 3 6 4
Day Weather Temperature Humidity Wind Play(yes/No
Day 1 Sunny Hot High Weak No
Day 2 Sunny Hot High Strong no
Day 3 Cloudy Hot High Weak Yes
Day 4 Rain Mild High Weak Yes
Day 5 Rain Cool Normal Weak Yes
Day 6 Rain Cool Normal Strong No
Day 7 Cloudy Cool Normal Strong Yes
Day 8 Sunny Mild High Weak No
Day 9 Sunny Cool Normal Weak Yes
Day 10 Rain Mild Normal Weak Yes
Day 11 Sunny Mild Normal Strong Yes
Day 12 Cloudy Mild High Strong Yes
Day 13 Cloudy Hot Normal Weak Yes
Day 14 Rain Mild High Strong No
Day Weather Temperature Humidity Wind Play(Yes/
No)
Day 1 Sunny Hot High Weak No
Day 2 Sunny Hot High Strong No
Day 8 Sunny Mild High Weak No
Day 9 Sunny Cool Normal Weak Yes
Day 11 Sunny Mild Normal Strong Yes
Fully Connected Layer
Fully connected layers are dense network of neurons.

Applied after convolutional and max pooling layers.

Classifies the output.

Associate features to a particular label.

You might also like