This Title All WIREs
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 2.111

Randomness in neural networks: an overview

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Neural networks, as powerful tools for data mining and knowledge engineering, can learn from data to build feature‐based classifiers and nonlinear predictive models. Training neural networks involves the optimization of nonconvex objective functions, and usually, the learning process is costly and infeasible for applications associated with data streams. A possible, albeit counterintuitive, alternative is to randomly assign a subset of the networks’ weights so that the resulting optimization task can be formulated as a linear least‐squares problem. This methodology can be applied to both feedforward and recurrent networks, and similar techniques can be used to approximate kernel functions. Many experimental results indicate that such randomized models can reach sound performance compared to fully adaptable ones, with a number of favorable benefits, including (1) simplicity of implementation, (2) faster learning with less intervention from human beings, and (3) possibility of leveraging overall linear regression and classification algorithms (e.g., 1 norm minimization for obtaining sparse formulations). This class of neural networks attractive and valuable to the data mining community, particularly for handling large scale data mining in real‐time. However, the literature in the field is extremely vast and fragmented, with many results being reintroduced multiple times under different names. This overview aims to provide a self‐contained, uniform introduction to the different ways in which randomization can be applied to the design of neural networks and kernel functions. A clear exposition of the basic framework underlying all these approaches helps to clarify innovative lines of research, open problems, and most importantly, foster the exchanges of well‐known results throughout different communities. WIREs Data Mining Knowl Discov 2017, 7:e1200. doi: 10.1002/widm.1200

An RW‐FNN architecture with two inputs, three hidden functions, and one output. Fixed connections are shown as dashed lines, whilst trainable connections are fixed lines.
[ Normal View | Magnified View ]
Depiction of an RC architecture with one output. Fixed connections are shown as dashed lines, whilst trainable connections are shown as solid lines. The reservoir is highlighted with a light blue background.
[ Normal View | Magnified View ]
Schematic representation of the kernel approximation process. The original, fixed feature mapping is shown in light green, while the randomized space to approximate the kernel evaluation is shown in light blue.
[ Normal View | Magnified View ]

Browse by Topic

Technologies > Machine Learning

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts