Artificial neural networks (ANNs) aim to simulate the biological neural activities. Interestingly, many “engineering” prospects in ANN have relied on motivations from cognition and psychology studies. So far, two important learning theories that have been subject of active research are the prototype and adaptive learning theories. The learning rules employed for ANNs can be related to adaptive learning theory, where several examples of the different classes in a task are supplied to the network for adjusting internal parameters. Conversely, the prototype-learning theory uses prototypes (representative examples); usually, one prototype per class of the different classes contained in the task. These prototypes are supplied for systematic matching with new examples so that class association can be achieved. In this paper, we propose and implement a novel neural network algorithm based on modifying the emotional neural network (EmNN) model to unify the prototype- and adaptive-learning theories. We refer to our new model as “prototype-incorporated EmNN”. Furthermore, we apply the proposed model to two real-life challenging tasks, namely, static hand-gesture recognition and face recognition, and compare the result to those obtained using the popular back-propagation neural network (BPNN), emotional BPNN (EmNN), deep networks, an exemplar classification model, and k-nearest neighbor.

INTRODUCTION

MACHINE intelligence is a field that aims to achieve various tasks such as face recognition [1], speaker identification [2], natural language processing [3], and document segmentation [4] based on motivations from the human cognition processing [5], [6]. Inasmuch as these tasks are somewhat “trivial” for humans, machines strive to perform competitively [7], [8]. It is the hope that we can grossly simulate machines with “thinking” or processing capabilities such that performance on the aforementioned tasks can be achieved with reasonably high accuracy. More important is that machines can boast of intelligence when such systems have the capability to learn (or adapt internal parameters) and upgrade its performance over time based on available experiential knowledge [9], [10]; this is analogous to learning in humans [11], [12]. However, for us to breakthrough in machine intelligence and vision, we must first understand the basis of learning and visual processing in humans [13], [14]. Unfortunately, there exist a number of different schools of thought on how (object recognition) learning is achieved in humans, with two considerably important and actively researched theories of learning in humans being the prototype and adaptive-learning theories [15], [16]. The proposed model in this paper draws engineering inspiration from both learning theories to realize improved learning. We give a sufficient discussion on the two theories which give insight into the remaining sections within this work.