Machine Learning

The problem we had with the perceptron were:

• only converged for linearly separable problems

• stopped places that did not look like they would generalize well

We need an algorithm that takes a more balanced approach: - finds a "middle ground"

decision boundary - can make decisions even when the data is not separable

for binary classification for positive (y=1) vs negative (y=0) class

for a probability p to belong to the positive class, the odds ratio is given by

if r>1 we are more likely to be in the positive class

if r<1 we are more likely to be in the negative class

to make it more symmetric we consider the log of r

#machinelearning #python #machinelearningproject #machinelearningassignments