This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2019.2945545, IEEE Access Author Name: Preparation of Papers for IEEE Access (February 2017) 2 VOLUME XX, 2017 Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000. Digital Object Identifier 10.1109/ACCESS.2017.Doi Number Comprehensive Review of Artificial Neural Network Applications to Pattern Recognition Oludare Isaac Abiodun 1 , Aman Jantan 2 , Abiodun Esther Omolara 3 , Kemi Victoria Dada 4 , Abubakar Malah Umar 5 , Okafor Uchenwa Linus 6 , Humaira Arshad 7 Abdullahi Aminu Kazaure 8 Usman Gana 9 , and Mahammad Ubale Kiru 10 . Correspondence authors: Aman Jantan 2 (aman@usm.my) and Oludare Isaac Abiodun 1 (aioludare@gmail.com) ABSTRACT The era of artificial neural network (ANN) began with a simplified application in many fields and remarkable success in pattern recognition (PR) even in manufacturing industries. Although significant progress achieved and surveyed in addressing ANN application to PR challenges, nevertheless, some problems are yet to be resolved like whimsical orientation (the unknown path that cannot be accurately calculated due to its directional position). Other problem includes; object classification, location, scaling, neurons behavior analysis in hidden layers, rule, and template matching. Also, the lack of extant literature on the issues associated with ANN application to PR seems to slow down research focus and progress in the field. Hence, there is a need for state-of-the-art in neural networks application to PR to urgently address the above-highlights problems for more successes. The study furnishes readers with a clearer understanding of the current, and new trend in ANN models that effectively addresses PR challenges to enable research focus and topics. Similarly, the comprehensive review reveals the diverse areas of the success of ANN models and their application to PR. In evaluating the performance of ANN models, some statistical indicators for measuring the performance of the ANN model in many studies were adopted. Such as the use of mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), and variance of absolute percentage error (VAPE). The result shows that the current ANN models such as GAN, SAE, DBN, RBM, RNN, RBFN, PNN, CNN, SLP, MLP, MLNN, Reservoir computing, and Transformer models are performing excellently in their application to PR tasks. Therefore, the study recommends the research focus on current models and the development of new models concurrently for more successes in the field. INDEX TERMS Artificial neural networks, application to pattern recognition, feedforward neural networks, feedback neural networks, hybrid models. I. INTRODUCTION Artificial neural networks (ANNs) are referred to as nonlinear statistical data models that replicate the role of biological NNs [1]. Statistical pattern approach has been the most commonly studied and utilizes in practice [2]. However, an artificial neural network (ANN) models have been attractive [3,4]. ANNs are increasingly attractive, effective, efficient, and successful in achieving pattern recognition (PR) in many problems [5,6]. Unlike conventional pattern approaches, ANN can easily model complex or multi complexes task [7,8]. The former conventional techniques applied to handle PR problems are classified into structural, statistical, and hybrid approaches [9]. However, both the statistical and structural approaches can produce unsatisfactory results if they are applied as a solution to complex PR problems only. For instance, in the application, the structural method can be weak and not be able to perform in handling noise patterns. Similarly, it can be weak and ineffective in resolving numerical semantic information challenges. Likewise, the statistical method is incapable of using information concerning patterns structures. Thus, the intuiting of both approaches combined attracted research attention which gives rise to a hybrid approach. However, nowadays the ANN models are used because they can yield a better result in PR problems even in multi complexes tasks. The function of ANN in PR is unique and flexible with remarkable success. PR is a computational paradigm used for the classification of raw data. PR embrace a plethora of approaches that provide the development of different applications in various field of endeavor. The practicability of these approaches is the intelligent human imitation. A pattern can be referred to as a set of items, objects, images, events, cases, situations, features or abstractions where facets of a set are alike in an unequivocal sense. According to Norbert Wiener, “Pattern is an arrangement, it is characterized by the sequence of the features of which it is made-off instead of inherent underlying of features,” [10]. Whereas, Watanabe defined a pattern as “an entity” [10]. It can also be defined by the unique or recurrent denominator amidst multiple samples of an entity. For example, common things in fingerprint images can define a pattern of a fingerprint. Hence, a pattern can either be a fingerprint image, a human face, a handwritten joined word, a barcode, Internet web page, or a