Blood Cell Type Identification Using Different Emotional Neural Network Models
The thought that machines could have emotions has so far been unacceptable by humans. However, few decades ago the idea of machines with intelligence was also ridiculed, but today not only we have developed intelligent machines, but we are also exploring many areas for their application with great success.We have always overlooked the emotional factors during machine learning and decision making; however, it is quite conceivable to artificially model some emotions in machine learning. This paper presents four emotional neural network models (EmNNs) that are based on the emotional back propagation (EmBP) learning algorithm. The EmNNs have emotional weights and two emotional parameters; anxiety and confidence, which are updated during learning. The four EmNN models differ in their topologies as a result of different input data coding methods. The performance of the EmNN models when applied to a blood cell type identification problem will be evaluated. Experimental results show that the additional emotional parameters and weights in all four models improve the identification rate as well as the classification time.
Keywords: Emotional neural network, EmBP, emotion modeling, anxiety and confidence, object identification, blood cells.