AU-NN: ANFIS Unit Neural Network

TL;DR

This paper introduces the AU-NN, a deep neural network composed of ANFIS neurons, demonstrating its effectiveness in classifying imagined words and detecting word segments with improved performance over traditional methods.

Contribution

The paper presents the novel AU-NN architecture, integrating ANFIS units into a deep neural network, and showcases its application in imagined word classification and incremental learning tasks.

Findings

Outperforms conventional methods in classification accuracy

Effective in incremental learning for imagined word detection

Decomposition-based classification improves robustness

Abstract

In this paper is described the ANFIS Unit Neural Network, a deep neural network where each neuron is an independent ANFIS. Two use cases of this network are shown to test the capability of the network. (i) Classification of five imagined words. (ii) Incremental learning in the task of detecting Imagined Word Segments vs. Idle State Segments. In both cases, the proposed network outperforms the conventional methods. Additionally, is described a process of classification where instead of taking the whole instance as one example, each instance is decomposed into a set of smaller instances, and the classification is done by a majority vote over all the predictions of the set. The codes to build the AU-NN used in this paper, are available on the github repository https://github.com/tonahdztoro/AU_NN.