Modified deep attractor neural networks for variability compensation in recognition tasks. (April 2022)

• Record Type: Journal Article
• Authors: Reza, Shaghayegh; Seyyedsalehi, Seyyed Ali; Seyyedsalehi, Seyyede Zohreh
• Is Part Of: Computers & electrical engineering. Volume 99(2022)
• Publication Date: 2022-04
• Subjects: Robust recognition -- Denoising autoencoders -- Deep attractor neural networks -- Variability compensation; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.107776
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Variability compensation techniques are essential for robust recognition systems. Denoising autoencoders can degrade variabilities in recognition tasks. Modified deep attractor neural network compensates and recognizes simultaneously. Variabilities are compensated by pulling samples to their corresponding attractors. Abstract: Some brain functions can be described with attractor formation in the human neural system. Various biologically-inspired models have employed this characteristic for memory representation, pattern completion and, noise reduction. Attractor neural networks are amongst these models capable of settling to stable patterns called attractors using their recurrent connections. Deep attractor neural networks (DANets) are relatively new models that utilize their attractors to separate the sources in the mixtures. In this paper, a modified version of DANets, variability compensator attractor neural network (VCANets); is proposed. This model compensates variabilities which are a common source of performance degradation in recognition tasks. For this purpose, significant modifications were applied to the structure and training procedure of DANets, including attractors' calculation, multi-task learning, curriculum learning, mining of challenging samples, and special mini-batch training procedure. Experiments on the MNIST and MNIST-C datasets for handwritten digit recognition and FARSDAT dataset for acoustic landmark recognition show that VCANet can effectively improve recognition accuracy and reduce unwanted variabilities. Graphical abstract: Image, graphical abstract