Course: More Data Mining with Weka

(A full index to the course appears at the end of Week 1.) Topic   Step Datasets Breast-cancer 5.2, 5.3, 5.4, 5.5, 5.11, 5.13   Credit-g 5.2, 5.3, 5.4, 5.5, …

(A full index to the course appears at the end of Week 1.) Topic   Step Datasets Breast-cancer 4.14   Credit-g 4.13, 4.15, 4.16   Diabetes 4.4   Glass 4.2, …

(A full index to the course appears at the end of Week 1.) Topic   Step Datasets Breast-cancer 3.8, 3.19   Contact-lenses 3.5   Credit-g 3.8, 3.19   Diabetes 3.7, …

(A full index to the course appears at the end of Week 1.) Topic   Step Datasets Diabetes 2.7   Glass 2.7   Ionosphere 2.2, 2.3, 2.5, 2.7   Iris …

At the end of each week is an index of topics covered that week. A full index to the course appears under DOWNLOADS, below. Topic   Step Datasets Breast-cancer 1.12 …

Thanks for taking this course. We hope you’ve enjoyed it. This course has extended your knowledge and experience of practical data mining, following on from Data Mining with Weka. We’ve …

Two questions loom large when embarking on a data mining project. First, how much training data is enough? And second, given that data mining algorithms generally have parameters, how do …

Neural networks are a computational approach based on a large collection of primitive units connected together in a simple, regular, way. Some people call the units “neurons,” and claim that …

There’s no magic in data mining – no universal “best” method. It’s an experimental science. This video reviews what this course has covered, and points out many things that it …

Remember the ARFF format? – we’ve been using it all along. But it’s more powerful than you have seen. For example, it can encode sparse data, which often greatly reduces …

Machine learning methods often involve several parameters, which should be optimized for best performance. Optimizing them manually is tedious, and also dangerous, because you risk overfitting the data (unless you …

How much data do you need? There is no easy answer; it depends on many features of the problem and dataset. One way to estimate it is to plot a …

In the last couple of videos I’ve been a bit negative about perceptrons and multilayer perceptrons – and the preceding quiz hasn’t exactly made a good case for them! But …

Let’s review the performance of multilayer perceptrons in the preceding quiz. First, 2 hidden layers never significantly outperform 1 hidden layer. Ignoring significance: 2 hidden layers are best for 1 …

Multilayer perceptrons are networks of perceptrons, networks of linear classifiers. In fact, they can implement arbitrary decision boundaries using “hidden layers”. Weka has a graphical interface that lets you create …