Inversion of feedforward neural networks: algorithms and applications

Abstract

Feedforward layered perceptron neural networks seek to capture a system mapping inferred by training data. A properly trained neural network is not only capable of mimicking the process responsible for generating the training data, but the inverse process as well. Neural network inversion procedures seek to find one or more input values that produce a desired output response for a fixed set of synaptic weights. There are many methods for performing neural network inversion. Multi-element evolutionary inversion procedures are capable of finding numerous inversion points simultaneously. Constrained neural network inversion requires that the inversion solution belong to one or more specified constraint sets. In many cases, iterating between the neural network inversion solution and the constraint set can successfully solve constrained inversion problems. This paper surveys existing methodologies for neural network inversion, which is illustrated by its use as a tool in query-based learning, sonar performance analysis, power system security assessment, control, and generation of codebook vectors.

Neural networks in satellite rainfall estimation

“…A trained NN can be analysed further to find out what type of inputs can generate a given output. Inversion methods such as that presented by Jensen et al (1999) can be applied to try to extract the assumptions the NN is making. Linden & Kindermann (1989), Linderman & Linden (1990) and Williams (1996) have also presented methods for the inversion of nets.…”

Reliable estimation of a neural network's domain of validity through interval analysis based inversion

“…A survey on these algorithms and related applications can be found in [4]. The authors of this paper formulate the inversion problem, analyze a number of techniques for solving this problem and present applications validating these techniques.…”

Solution for Ill-Posed Inverse Kinematics of Robot Arm by Network Inversion

“…The network inversion method has been proposed for solving inverse problems by using a multilayer neural network [6]. In this method, inverse problems are solved by using a trained multilayer neural network inversely to estimate the corresponding input from the given output [7,8]. The advantages of this method are easiness of the direct modeling by learning and adaptive estimation of the inverse solution.…”