Loading...

Cellular Learning Automata and Its Applications in Pattern Recognition

Ahangaran, Meysam | 2009

923 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 40227 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Beigy, Hamid
  7. Abstract:
  8. Cellular learning automata (CLA) is a distributed computational model that is introduced recently. This model is combination of cellular automata (CA) and learning automata (LA) and is used in many applications such as image processing, channel assignment in cellular networks, VLSI placement, rumor diffusion and modeling of commerce networks, and obtained acceptable results in these applications. This model consists of computational units called cells and each cell has one or more learning automata. In each stage, each automaton chooses an action from its actions set and applies it to the environment. Each cell has some neighboring cells that constitute its local environment. The local rule of the CLA generates a reinforcement signal to each cell on the basis of neighboring LAs action. Then the LA residing in each cell updates its internal state based on the reinforcement signal, and this process continues until the desired behavior is obtained. This model accepts only reinforcement signal as input. In this thesis, we introduce a new model of CLA in which each cell gets input from external environment in addition to the reinforcement signal. This input represents the current state of the environment. In each stage the environment informs CLA by sending its state. Then each automaton selects an action and applies to the environment. The environment evaluates the action and supplies a reinforcement signal. Finally, LAs update their internal states on the basis of chosen action, given state and the reinforcement signal. Then we propose some algorithms based on the proposed model including classification, clustering and image segmentation. The exprimental results show that the proposed model has good performance in given applications and in many cases has better results in comparison with existing algorithms
  9. Keywords:
  10. Clustering ; Pattern Recognition ; Self-Organizing Map (SOM) ; Stochastic Cellular Learning Automata ; Intra Similarity Measure ; Inter Similarity Measure ; Reinforcement Signal

 Digital Object List

 Bookmark

No TOC