Feature scaling and the type of distance metric used in nearest neighbour algorithms has a big effect on performance. This data science training video talks about this and other nearest neighbour tips and tricks.
The nearest neighbour algorithm can also be used for classification and regression purposes. Find out how in this training video.
The idea of similarity transcends problem boundaries. From recommendations to classification, learn how the nearest neighbour algorithm is not only useful but also very simple.
Often we can't visualise the decision boundary because there are too many dimensions. This training video shows you how to visualise overfitting when you have a high dimensional problem.
To prevent fooling ourselves into thinking we are doing well, we hold back some data. Learn how in this training video.
Overfitting is one of the most common data science problems. This training video explains why should generalise and prevent overfitting.
Sometimes linear decision boundaries aren't complex enough to perform well. This training video shows you how to transform your data to produce nonlinear boundaries.
This training video explains how the most popular linear classification algorithms work.
This training video explains why we need gradient descent and how it works.
This section introduces using linear models for regression. Later we will expand our use of linear models for classification purposes.
Case studies and industry analysis from our team. No hype, roughly monthly.