Transformer model: Explainability and prospectiveness

Abstract

The purpose of Artificial Intelligence(AI) is to simulate learning process of human brain by strong computing power and appropriate algorithm, so that the machine can develop judging ability at work as human. Current AI mainly relies on Deep Learning model which is based on artificial neural network, like Convolutional Neural Network(CNN) in computer visualization, but that also takes with some defects. This paper introduces defects of CNN and discusses Transformer model in solving unexplainability of traditional CNN algorithm. To discuss why the Transformer model and attention mechanism are considered as the way to AI intelligibility.