FANRE: A Fast Adaptive Neural Regression Estimator [1 citations — 0 self]
Abstract:
Abstract. In this paper, a fast adaptive neural regression estimator named FANRE is proposed. FANRE exploits the advantages of both Adaptive Resonance Theory and Field Theory while contraposing the characteristic of regression problems. It achieves not only impressive approximating results but also fast learning speed. Besides, FANRE has incremental learning ability. When new instances are fed, it does not need retrain the whole training set. In stead, it could learn the knowledge encoded in those instances through slightly adjusting the network topology when necessary. This characteristic enable FANRE work for real-time online learning tasks. Experiments including approximating line, sine and 2-d Mexican Hat show that FANRE is superior to BP kind algorithms that are most often used in regression estimation on both approximating effect and training time cost. 1.
Citations
| 431 | Learning representation by back propagating errors – Rumelhart, Hinton, et al. - 1986 |
| 302 | A Massively Parallel Architecture for a SelfOrganizing Neural – Carpenter, Grossberg - 1987 |
| 255 | Adaptive pattern classification and universal recoding: Part I. Parallel development and codings of neural feature detectors – Grossberg - 1976 |
| 177 | Fuzzy ARTMAP: A Neural Network Architecture for Incremental Learning of Analog Multidimensional Maps – Carpenter, Grossberg, et al. - 1992 |
| 41 | SuperSAB: Fast adaptive back propagation with good scaling properties. Neural Networks – Tollenaere - 1990 |
| 17 | Rule-Based Regression – Weiss, Indurkhya - 1993 |
| 10 | FANNC: A Fast Adaptive Neural Network Classifier – Zhou, Chen, et al. - 2000 |
| 1 | et al. A Relaxation Model for Memory with High Storage Density – Bachmann, Cooper, et al. - 1987 |
