Incremental Learning of Chunk Data for Online Pattern Classification Systems

Abstract

This paper presents a pattern classification system in which feature extraction and classifier learning are simultaneously carried out not only online but also in one pass where training samples are presented only once. For this purpose, we have extended incremental principal component analysis (IPCA) and some classifier models were effectively combined with it. However, there was a drawback in this approach that training samples must be learned one by one due to the limitation of IPCA. To overcome this problem, we propose another extension of IPCA called chunk IPCA in which a chunk of training samples is processed at a time. In the experiments, we evaluate the classification performance for several large-scale data sets to discuss the scalability of chunk IPCA under one-pass incremental learning environments. The experimental results suggest that chunk IPCA can reduce the training time effectively as compared with IPCA unless the number of input attributes is too large. We study the influence of the size of initial training data and the size of given chunk data on classification accuracy and learning time. We also show that chunk IPCA can obtain major eigenvectors with fairly good approximation.

An Online Malicious Spam Email Detection System Using Resource Allocating Network with Locality Sensitive Hashing

“…Accumulation ratio ( ) l A U is the ratio of input components in the approximated subspace over those in the whole input space [17]. Giving a proper value of a θ based on a tolerant approximation error, a proper number of hash functions is automatically determined by selecting the number of partitions P via the cross-validation.…”

Evolving Spiking Neural Networks and Neurogenetic Systems for Spatio- and Spectro-Temporal Data Modelling and Pattern Recognition

“…regression techniques; MLP; eSNN; nearest-neighbour techniques; incremental LDA [85]. State vector transformation, before classification can be done with the use of adaptive incremental transformation functions, such as incremental PCA [84].…”

Evolving spiking neural networks for spatio-and spectro-temporal pattern recognition

“…ECOS learn local models from data through clustering of the data and associating a local output function for each cluster represented in a connectionist structure. They can learn incrementally single data items or chunks of data and also incrementally change their input features [40,41]. Elements of ECOS have been proposed as part of the classical NN models, such as SOM, RBF, FuzyARTMap, Growing neural gas, neuro-fuzzy systems, RAN (see [25]).…”

“…regression techniques; MLP; nearest-neighbour techniques; incremental LDA [41]. State vector transformation, before classification can be done with the use of adaptive incremental transformation functions, such as incremental PCA [40].…”