A new ARTMAP-based neural network for incremental learning

An incremental neural network with a reduced architecture

This paper proposes a technique, called Evolving Probabilistic Neural Network (ePNN), that presents many interesting features, including incremental learning, evolving architecture, the capacity to learn continually throughout its existence and requiring that each training sample be used only once in the training phase without reprocessing. A series of experiments was performed on data sets in the public domain; the results indicate that ePNN is superior or equal to the other incremental neural networks evaluated in this paper. These results also demonstrate the advantage of the small ePNN architecture and show that its architecture is more stable than the other incremental neural networks evaluated. ePNN thus appears to be a promising alternative for a quick learning system and a fast classifier with a low computational cost.

AN INCREMENTAL FRAMEWORK BASED ON CROSS-VALIDATION FOR ESTIMATING THE ARCHITECTURE OF A MULTILAYER PERCEPTRON

We define the problem of optimizing the architecture of a multilayer perceptron (MLP) as a state space search and propose the MOST (Multiple Operators using Statistical Tests) framework that incrementally modifies the structure and checks for improvement using cross-validation. We consider five variants that implement forward/backward search, using single/multiple operators and searching depth-first/breadth-first. On 44 classification and 30 regression datasets, we exhaustively search for the optimal and evaluate the goodness based on: (1) Order, the accuracy with respect to the optimal and (2) Rank, the computational complexity. We check for the effect of two resampling methods (5 × 2, ten-fold cv), four statistical tests (5 × 2 cv t, ten-fold cv t, Wilcoxon, sign) and two corrections for multiple comparisons (Bonferroni, Holm). We also compare with Dynamic Node Creation (DNC) and Cascade Correlation (CC). Our results show that: (1) On most datasets, networks with few hidden units are optimal, (2) forward searching finds simpler architectures, (3) variants using single node additions (deletions) generally stop early and get stuck in simple (complex) networks, (4) choosing the best of multiple operators finds networks closer to the optimal, (5) MOST variants generally find simpler networks having lower or comparable error rates than DNC and CC.

High-Speed Maximum Power Point Tracker for Photovoltaic Systems Using Online Learning Neural Networks

Photo Voltaic (PV) devices have a Maximum Power Point (MPP) at which they generate maximum power. Because the MPP depends on solar radiation and PV panel temperature, it is not constant over time. A Maximum Power Point Tracker (MPPT) is widely used to continuously obtain maximum power, but if the solar radiation changes rapidly, the efficiency of most classic MPPT (e.g., the Perturbation and Observation (P&O) method) reduces. MPPT controllers using neural network respond quickly to rapidly changing solar radiation but must usually undergo prelearning using PV-specific data, so we propose MPPT that handles both online learning of PV properties and feed-forward control of the DC-DC converter with a neural network. Both simulation results and actual device performance using our proposed MPPT showed great efficiency even under rapidly changing solar radiation. Our proposal is implemented using a small microcomputer using low computational power.