AU-NN: ANFIS Unit Neural Network
This work addresses incremental learning and classification challenges in brain-computer interfaces, but it appears incremental as it applies a known ANFIS method in a new neural network structure.
The paper tackles the problem of classifying imagined words and detecting imagined word segments versus idle states by introducing the ANFIS Unit Neural Network, where each neuron is an independent ANFIS, and it outperforms conventional methods in both tasks.
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.