Deep Convolutional Generalized Classifier Neural Network

• Published in: Neural processing letters 2020-06, Vol.51 (3), p.2839-2854
• Main Authors: Sarigul, Mehmet, Ozyildirim, B. Melis, Avci, Mutlu
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Artificial neural networks; Back propagation networks; Classification; Classifiers; Codes; Complex Systems; Computational Intelligence; Computer Science; Datasets; Deep learning; Experiments; Feature extraction; Hybrid structures; Machine learning; Network topologies; Neural networks; Neurons; Pattern recognition; Performance evaluation; Support vector machines
• ISSN: 1370-4621; 1573-773X
• DOI: 10.1007/s11063-020-10233-8

Up to date technological implementations of deep convolutional neural networks are at the forefront of many issues, such as autonomous device control, effective image and pattern recognition solutions. Deep neural networks generally utilize a hybrid topology of a feature extractor containing convolutional layers followed by a fully connected classifier network. The characteristic and quality of the produced features differ according to the deep learning structure. In order to get high performance, it is necessary to choose an effective topology. In this study, a novel topology based hybrid structure named as Deep Convolutional Generalized Classifier Neural Network and its learning algoritm are introduced. This novel structure allows the deep learning network to extract features with the desired characteristics. This ensures high performance classification, even for relatively small deep learning networks. This has led to many novelties such as principal feature analysis, better learning ability, one-pass learning for classifier part, new error computation and backpropagation approach for filter weights. Two experiment sets were performed to measure the performance of DC-GCNN. In the first experiment set, DC-GCNN was compared with clasical approach on 10 different datasets. DC-GCNN performed better up to 44.45% for precision, 39.69% for recall and 42.57% for F1-score. In the second experiment set, DC-GCNN’s performance was compared with alternative methods on larger datasets. Proposed structure performed better than alternative deep learning based classifier structures on CIFAR-10 and MNIST datasets with 89.12% and 99.28% accuracy values.