Notes

Neural networks are the building blocks of deep learning. Here we break down how they work.

Here I breakdown the difference between unsupervised and supervised learning, and the most known algorithms used in each.

Support vector machines can be used for regression, classification, and outlier detection.

The bias-variance tradeoff is a very well known phenomenon encountered when solving for overfitting.

Logistic regression uses a sigmoid function to perform binary classification, i.e. when you can linearly separate two classes of data from each other.

Linear regression is useful for finding the linear relationship between the independent and dependent variables of a dataset.