This paper presents a neural network based on adaptive resonance theory, named distributed art (adaptive resonance theory) & HS-artMAP (Hyper-spherical artMAP network), applied to the electric load forecasting pro...
详细信息
This paper presents a neural network based on adaptive resonance theory, named distributed art (adaptive resonance theory) & HS-artMAP (Hyper-spherical artMAP network), applied to the electric load forecasting problem. The distributed art combines the stable fast learning capabilities of winner-take-all art systems with the noise tolerance and code compression capabilities of multi-layer perceptions. The HS-artMAP, a hybrid of an RBF (Radial Basis Function)-network-like module which uses hyper-sphere basis function substitute the Gaussian basis function and an art-like module, performs incremental learning capabilities in function approximation problem. The HS-artMAP only receives the compressed distributed coding processed by distributed art to deal with the proliferation problem which artMAP (adaptive resonance theory map) architecture often encounters and still performs well in electric load forecasting. To demonstrate the performance of the methodology, data from New South Wales and Victoria in Australia are illustrated. Results show that the developed method is much better than the traditional BP and single HS-artMAP neural network. (c) 2010 Elsevier Ltd. All rights reserved.
A class of adaptive resonance theory (art) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. distributed art neural networks combine the stable fast lear...
详细信息
A class of adaptive resonance theory (art) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. distributed art neural networks combine the stable fast learning capabilities of winner-take-all art systems with the noise tolerance and code compression capabilities of multilayer perceptrons. With a winner-take-all code, the unsupervised model dart reduces to fuzzy art and the supervised model dartMAP reduces to fuzzy artMAP. With a distributed code, these networks automatically apportion learned changes according to the degree of activation of each coding node, which permits fast as well as slow learning without catastrophic forgetting. distributed art models replace the traditional neural network path weight with a dynamic weight equal to the rectified difference between coding node activation and an adaptive threshold Thresholds increase monotonically during learning according to a principle of atrophy due to disuse. However, monotonic change at the synaptic level manifests itself as bidirectional change at the dynamic level, where the result of adaptation resembles long-term potentiation (LTP) for single-pulse or low frequency test inputs but can resemble long-term depression (LTD) for higher frequency test inputs. This paradoxical behavior is traced to dual computational properties of phasic and tonic coding signal components. A parallel distributed match-reset-search process also helps stabilize memory. Without the match-reset-search system, dart becomes a type of distributed competitive learning network. (C) 1997 Elsevier Science Ltd.
暂无评论