Self-Improving Generative Artificial Neural Network for Pseudorehearsal Incremental Class Learning

• Published in: Algorithms 2019-10, Vol.12 (10), p.206
• Main Authors: Mellado, Diego, Saavedra, Carolina, Chabert, Steren, Torres, Romina, Salas, Rodrigo
• Format: Article
• Language: English
• Subjects: Artificial neural networks; catastrophic interference; Deep learning; generative neural networks; incremental learning; Learning; Machine learning; Methods; Modules; Neural networks; novelty detection; Sensors
• ISSN: 1999-4893; 1999-4893
• DOI: 10.3390/a12100206

Deep learning models are part of the family of artificial neural networks and, as such, they suffer catastrophic interference when learning sequentially. In addition, the greater number of these models have a rigid architecture which prevents the incremental learning of new classes. To overcome these drawbacks, we propose the Self-Improving Generative Artificial Neural Network (SIGANN), an end-to-end deep neural network system which can ease the catastrophic forgetting problem when learning new classes. In this method, we introduce a novel detection model that automatically detects samples of new classes, and an adversarial autoencoder is used to produce samples of previous classes. This system consists of three main modules: a classifier module implemented using a Deep Convolutional Neural Network, a generator module based on an adversarial autoencoder, and a novelty-detection module implemented using an OpenMax activation function. Using the EMNIST data set, the model was trained incrementally, starting with a small set of classes. The results of the simulation show that SIGANN can retain previous knowledge while incorporating gradual forgetfulness of each learning sequence at a rate of about 7% per training step. Moreover, SIGANN can detect new classes that are hidden in the data with a median accuracy of 43 % and, therefore, proceed with incremental class learning.