Toward the scalability of neural networks through feature selection

In the past few years, the bottleneck for machine learning developers is not longer the limited data available but the algorithms inability to use all the data in the available time. For this reason, researches are now interested not only in the accuracy but also in the scalability of the machine learning algorithms. To deal with large-scale databases, feature selection can be helpful to reduce their dimensionality, turning an impracticable algorithm into a practical one. In this research, the influence of several feature selection methods on the scalability of four of the most well-known training algorithms for feedforward artificial neural networks (ANNs) will be analyzed over both classification and regression tasks. The results demonstrate that feature selection is an effective tool to improve scalability.

► Researchers must now study not only accuracy but also scalability.
► Feature selection (FS) can be useful to reduce the dimensionality of large data sets.
► The influence of FS on the scalability of training algorithms for ANNs is analyzed.
► FS allows algorithms to train on some datasets where it was unfeasible.
► FS as a preprocessing step is beneficial for the scalability of ANNs.