ART 3: Hierarchical search using chemical transmitters in self-organizing pattern recognition architectures. A model to implement parallel search of compressed or distributed pattern recognition codes in a neural network hierarchy is introduced. The search process functions well with either fast learning or slow learning, and can robustly cope with sequences of asynchronous input patterns in real-time. The search process emerges when computational properties of the chemical synapse, such as transmitter accumulation, release, inactivation, and modulation, are embedded within an Adaptive Resonance Theory architecture called ART 3. Formal analogs of ions such as Na− and Ca2− control nonlinear feedback interactions that enable presynaptic transmitter dynamics to model the postsynaptic short-term memory representation of a pattern recognition code. Reinforcement feedback can modulate the search process by altering the ART 3 vigilance parameter or directly engaging the search mechanism. The search process is a form of hypothesis testing capable of discovering appropriate representations of a nonstationary input environment.

References in zbMATH (referenced in 27 articles )

Showing results 1 to 20 of 27.
Sorted by year (citations)

1 2 next

  1. Zou, Shaofen; Chen, Yuming; Ma, Jianfu; Wu, Jianhong: Delay for the capacity-simplicity dilemma in associative memory attractor networks (2012)
  2. Grossberg, Stephen; Markowitz, Jeffrey; Cao, Yongqiang: On the road to invariant recognition: explaining tradeoff and morph properties of cells in inferotemporal cortex using multiple-scale task-sensitive attentive learning (2011) ioport
  3. Amis, Gregory P.; Carpenter, Gail A.: Self-supervised ARTMAP (2010)
  4. Du, K.-L.: Clustering: a neural network approach (2010)
  5. Zhang, WenJun: Computational ecology. Artificial neural networks and their applications (2010)
  6. Kasabov, Nikola: Integrative connectionist learning systems inspired by nature: Current models, future trends and challenges (2009)
  7. Levine, Daniel S.: Brain pathways for cognitive-emotional decision making in the human animal (2009) ioport
  8. Jia, Peng; Yin, Junsong; Hu, Dewen; Zhou, Zongtan: Retrograde adaptive resonance theory based on the role of nitric oxide in long-term potentiation (2007) ioport
  9. Tan, Meng Piao; Broach, James R.; Floudas, Christodoulos A.: A novel clustering approach and prediction of optimal number of clusters: global optimum search with enhanced positioning (2007)
  10. Wahab, A.; Ng, G. S.; Jonatan, A.: Integrated biometric verification system using soft computing approach (2007) ioport
  11. Dagher, Issam: Art networks with geometrical distances (2006)
  12. Bagirov, A. M.; Rubinov, A. M.; Soukhoroukova, N. V.; Yearwood, J.: Unsupervised and supervised data classification via nonsmooth and global optimization (with comments and rejoinder) (2003)
  13. Martí, Luis; Policriti, Alberto; García, Luciano: AppART: An ART hybrid stable learning neural network for universal function approximation (2002)
  14. Aisbett, Janet; Gibbon, Greg: A general formulation of conceptual spaces as a meso level representation (2001)
  15. Harrison, Robert F.; Cross, Simon S.; Kennedy, R. Lee; Lim, Chee Peng; Downs, Joseph: Adaptive resonance theory: a foundation for `apprentice’ systems in clinical decision support? (2001)
  16. Contreras-Vidal, José L.; Schultz, Wolfram: A predictive reinforcement model of dopamine neurons for learning approach behavior (1999)
  17. Abe, Shigeo: Neural networks and fuzzy systems. Theory and applications. Foreword by Anca Ralescu (1997)
  18. Lim, Chee Peng; Harrison, Robert F.: An incremental adaptive network for online supervised learning and probability estimation. (1997) ioport
  19. Lim, Chee Peng; Harrison, Robert F.: An incremental adaptive network for online supervised learning and probability estimation. (1997) ioport
  20. Raijmakers, Maartje; Molenaar, Peter C. M.: Exact ART: A complete implementation of an ART network. (1997) ioport

1 2 next