Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Bottom-up learning of hierarchical models in a class of deterministic POMDP environments

Itoh H., Fukumoto H., Wakuya H., Furukawa T.

International Journal of Applied Mathematics and Computer Science

2015

Vol. 25, no. 3

597--615

The theory of partially observable Markov decision processes (POMDPs) is a useful tool for developing various intelligent agents, and learning hierarchical POMDP models is one of the key approaches for building such agents when the environments of the agents are unknown and large. To learn hierarchical models, bottom-up learning methods in which learning takes place in a layer-by-layer manner from the lowest to the highest layer are already extensively used in some research fields such as hidden Markov models and neural networks. However, little attention has been paid to bottom-up approaches for learning POMDP models. In this paper, we present a novel bottom-up learning algorithm for hierarchical POMDP models and prove that, by using this algorithm, a perfect model (i.e., a model that can perfectly predict future observations) can be learned at least in a class of deterministic POMDP environments.

Building a cognitive map using an SOM2

Tokunaga K., Furukawa T.

Journal of Automation Mobile Robotics and Intelligent Systems

2010

Vol. 4, No. 2

39-47

In this paper, we propose a new method for building an environmental map in a self-organizing manner using visual information from a mobile robot. This method is based on a Higher Rank of Self-Organizing Map (SOM ), in which Kohonen’s SOM is extended to create a map of data distributions (set of manifolds). It is expected that the “SOM” is capable of creating an environmental map in a self-organizing manner from visual information, since the set of visual information obtained from each position in the environment forms a manifold at every position. We also show the effectiveness of the proposed method.