Abstract Catastrophic forgetting in neural networks during incremental learning remains a challenging problem. Previous research investigated catastrophic fully connected networks, with some earlier work exploring activation functions and algorithms. Applications of have been extended to include similarity learning. Understanding how loss would be affected by is significant interest. Our invest...

This paper develops the incremental learning by using chaotic neurons, which is called “on-demand learning” at its developing time. The incremental learning unites the learning process and the recall process in the associative memories. This learning method uses the features of the chaotic neurons which were first developed by Prof. Aihara. The features include the spatio-temporal sum of the in...

Automatic pattern classifiers that allow for on-line incremental learning can adapt internal class models efficiently in response to new information without retraining from the start using all training data and without being subject to catastrophic forgeting. In this paper, the performance of the fuzzy ARTMAP neural network for supervised incremental learning is compared to that of supervised b...

Model based learning systems usually face to a problem of forgetting as a result of the incremental learning of new instances. Normally, the systems have to re-learn past instances to avoid this problem. However, the re-learning process wastes substantial learning time. To reduce learning time, we propose a novel incremental learning system, which consists of two neural networks: a main-learnin...

A new incremental support vector machine (SVM) algorithm is proposed which is based on multiple kernel learning. Through introducing multiple kernel learning into the SVM incremental learning, large scale data set learning problem can be solved effectively. Furthermore, different punishments are adopted in allusion to the training subset and the acquired support vectors, which may help to impro...

Due to catastrophic forgetting, deep learning remains highly inappropriate when facing incremental learning of new classes and examples over time. In this contribution, we introduce Transfer Incremental Learning using Data Augmentation (TILDA). TILDA combines transfer learning from a pre-trained Deep Neural Network (DNN) as feature extractor, a Nearest Class Mean (NCM) inspired classifier and m...

Support vector ordinal regression (SVOR) is a popular method to tackle ordinal regression problems. However, until now there were no effective algorithms proposed to address incremental SVOR learning due to the complicated formulations of SVOR. Recently, an interesting accurate on-line algorithm was proposed for training ν-support vector classification (ν-SVC), which can handle a quadratic form...

SwiftFile is an intelligent assistant that helps users organize their e-mail into folders. SwiftFile uses a text classifier to predict where each new message is likely to be filed by the user and provides shortcut buttons to quickly file messages into one of its predicted folders. One of the challenges faced by SwiftFile is that the user’s mail-filing habits are constantly changing — users are ...

Real membership authentication applications require machines to learn from stream data while making a decision as accurately as possible whenever the authentication is needed. To achieve that, we proposed a novel algorithm which authenticated membership by a one-pass incremental principle component analysis(IPCA) learning. It is demonstrated that the proposed algorithm involves an useful increm...