O'Reilly logo

Neural Network Programming with Java by Fábio M. Soares, Alan M.F. Souza

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

A special type of activation function – Logistic regression

We've covered that neural networks can work as data classifiers by establishing decision boundaries onto data in the hyperspace. Such a boundary can be linear in the case of perceptrons or nonlinear in the case of other neural architectures such as MLPs, Kohonen, or Adaline. The linear case is based on linear regression, on which the classification boundary is literally a line, as shown in the preceding figure. If the scatter chart of the data looks like that shown in the following figure, then a nonlinear classification boundary is needed.

A special type of activation function – Logistic regression

Neural networks are in fact a great nonlinear classifier, ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required