A neural tree for classification using convex objective function

作者：Rani Asha^*; Foresti Gian Luca; Micheloni Christian

来源：Pattern Recognition Letters, 2015, 68: 41-47.

DOI：10.1016/j.patrec.2015.08.017

• Neural tree
• Artificial neural networks (ANNs)
• Mean squared error
• Pattern classification
• Perceptron
• Convex optimization

In this paper, we propose a neural tree classifier, called the convex objective function neural tree (COF-NT), which has a specialized perceptron at each node. The specialized perception is a single layer feed-forward perception which calculates the errors before the neuron's non-linear activation function instead of after them. Thus, the network parameters are independent of non-linear activation functions, and subsequently, the objective function is a convex objective function. The solution can be easily obtained by solving a system of linear equations which will require less computational power than conventional iterative methods. During the training, the proposed neural tree classifier divides the training set into smaller subsets by adding new levels to the tree. Each child perception takes forward the task of training done by its parent perceptron on the superset of this subset. Thus, the training is done by a number of single layer perceptrons (each perception carrying forward the work done by its ancestors) that each the global minima in a finite number of steps. The proposed algorithm has been tested on available benchmark datasets and the results are promising in terms of classification accuracy and training time.

• 出版日期2015-12-15