Human learns incidents by own actions and reflects them on the subsequent action as own experiences. These experiences are memorized in his brain and recollected if necessary. This research incorporates such an intell...
详细信息
ISBN:
(纸本)9788995003893
Human learns incidents by own actions and reflects them on the subsequent action as own experiences. These experiences are memorized in his brain and recollected if necessary. This research incorporates such an intelligent information processing mechanism, and applies it to an autonomous agent that has three main functions: learning, memorization and associative recollection. In the proposed system, an actor-critic type reinforcement learning method is used for learning. Auto-associative chaotic neural network is also used like mutual associative memory system. Moreover, the memory part has an adaptive hierarchical layered structure of the memory module that consists of chaotic neural networks in consideration of the adjustment to non-MDP (Markov Decision Process) environment. Finally, effectiveness of this proposed method is verified through the simulation applied to the maze-searching problem.
This paper proposes a new memorystructure for the. real-time search with the computational resource boundary. In the proposed memory, each memory is hierarchically stored based on the frequency recall. Moreover, the ...
详细信息
ISBN:
(纸本)078037620X
This paper proposes a new memorystructure for the. real-time search with the computational resource boundary. In the proposed memory, each memory is hierarchically stored based on the frequency recall. Moreover, the number of checked memories is varied based on the available computational resource for the action acquisition in order to treat the trade-off between the computational amount for the memory retrieval and the one of the search. Men the search system utilises stored memories, the one with the highest frequency of recall is started checking from. This makes the efficient retrieval possible even if the available computational resource for the memory retrieval is not enough. In this paper, the proposed method is applied to the action acquisition for autonomous mobile robots in the moving obstacles' avoidance problem. Its usefulness is shown through some experimental results and the verification.
The introduction of a hierarchical memory structure into a cascade associative memory model for storing hierarchically correlated patterns improves the storage capacity and the size of the basins of attraction remarka...
详细信息
The introduction of a hierarchical memory structure into a cascade associative memory model for storing hierarchically correlated patterns improves the storage capacity and the size of the basins of attraction remarkably. A learning algorithm groups descendants (second-level patterns) according to their ancestors (first-level ones), and organizes the memorystructure in a weight matrix where the groups are memorized separately. The weight matrix is, thus, in the form of a pile of covariance matrices, each of which is responsible for recalling only the descendants of each ancestor. Putting it simply, the model is multiplex associative memory. The recalling process proceeds as follows: the model first recalls the ancestor of a target descendant. Then, the dynamics with dynamic threshold combines the ancestor and the weight matrix to activate the covariance matrix for recalling only the descendants of the ancestor. This mechanism suppresses the cross-talk noise generated by the descendants of the other ancestors, and the recalling ability is enhanced. (C) 2000 Elsevier Science Ltd. All rights reserved.
暂无评论