VCI-LSTM: Vector Choquet Integral-Based Long Short-Term Memory

Choquet integral is a widely used aggregation operator on 1-D and interval-valued information, since it able to take into account the possible interaction among data. However, there are many cases where information taken vectorial, such as long short-term memories (LSTM). LSTM units kind of recurrent neural networks that have become one most powerful tools deal with sequential they power controlling flow. In this article, we first generalize standard admit an input composed by $n$ -dimensional vectors, which produces vector output. We study several properties construction methods integrals (VCIs). Then, use in place summation operator, introducing way new VCI-LSTM architecture. Finally, proposed two problems: 1) image classification; 2) text classification.