From the course: Spark for Machine Learning & AI
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Summary of classification algorithms - Apache Spark Tutorial
From the course: Spark for Machine Learning & AI
Summary of classification algorithms
- [Instructor] We've looked at a few classification algorithms. Naive Bayes did not work very well with the Iris data set. The multilayer perceptron worked well, but required us to make some configuration decisions, with regards to how to structure the neural net. Decision trees worked as well as the multilayer perceptron, but didn't require us to make any configuration decisions. In general, when working with classification algorithms it's helpful to experiment with a number of different algorithms and a number of different configurations, if that's required by the algorithm. Naive Bayes can work well in some cases. For example, if the attributes in your data set are what is known as independent of each other. That is, they don't tightly correlate with each other. In other cases, when you have non-linear relationships between data elements, the multilayer perceptron is a good option. Decision trees are a good option in many cases and it's worth starting with decision trees and then…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.