Search

Partial observability, or the inability of an agent to fully observe the state of its environment, exists in many real-world problem domains. However, most cognitive architectures do not have a theoretical foundation that allows for a systematic approach to handling partial observability. To address this issue, in this paper, we propose a novel cognitive architecture based on the theory of partially observable Markov decision processes (POMDPs). We focus on one of the most fundamental cognitive architectures, the blackboard architecture, and re-formulate it using the POMDP framework so that the agent can automatically decide how to use its information processing modules in partially observable environments. We propose a two-layer POMDP model for the blackboard architecture in which one layer models the dynamics of the environment and the other layer models the dynamics of the blackboard and knowledge sources within the agent. We also provide a planning method to find the optimal actions for the two-layer POMDP model based on the partially observable upper confidence bounds applied to trees (PO-UCT) algorithm. We validate the proposed architecture in both numerical and real-robot experiments.

Humanoid robots are expected to perform various jobs replacing human beings, but it is difficult for non-expert users to control them. To control humanoid robots easily, various motion imitation systems, in which a humanoid robot does the same motion as a human teacher, have been studied. In the present study, we make two contributions to building easy-to-use imitation systems. The first contribution is a flexible learning system that enables both synchronous real-time imitation, in which the robot imitates human motion almost immediately, and batch imitation, in which the robot’s motion is optimized more accurately after longer measurement of human motion. We use an efficient inference-based optimization method to enable both learning modes. The other contribution is an auditory user interface that accepts voice commands from the user and at the same time identifies the target person to be imitated. This enables the user to easily use the imitation system even when other people are present. Experimental results show that the proposed system can be used in both imitation modes and that it can identify the target person.

One of the attractive features which a self-organizing map (SOM) possesses is a topology-preserving projection from the input layer to the competitive layer. Generally speaking, its correspondence is developed through training based on information representations of the applied multi-dimensional data. A developed feature map in the competitive layer enables us easy to understand some underlying rules visually. By the way, an analysis of Saga Prefectural sightseeing information by a SOM has been tried so far. According to the results of preceding studies, applied various topics are divided into several groups successfully. Nevertheless, there are some items not reflected in them at all. This fact implies that representations of the applied data are not appropriate to develop the feature map which we have intended in advance. Then, to overcome this tough problem, a simple idea to emphasize particular items depending on our interests is introduced as pre-synaptic processing. As a result of some computer simulations, it is confirmed that the developed feature maps are modified adaptively depending on the emphasized coefficient. And, it is concluded that the proposed simple method is effective.

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

When developing a classifier using various objective functions, it is important to compare the performances of the classifiers. Although there are statistical analyses of objective functions for classifiers, simulation results can provide us with direct comparison results and in this case, a comparison criterion is considerably critical. A Receiver Operating Characteristics (ROC) graph is a simulation technique for comparing classifiers and selecting a better one based on a performance. In this paper, we adopt the ROC graph to compare classifiers trained by mean-squared error, cross-entropy error, classification figure of merit, and the n-th order extension of cross-entropy error functions. After the training of feed-forward neural networks using the CEDAR database, the ROC graphs are plotted to help us identify which objective function is better.

In the preceding studies, an analysis of Saga Prefectural sightseeing information by a Self-Organizing Map (SOM) has been tried. And recent development on Information and Communication Technology (ICT) will help us to access any results via the mobile devices easily. This is why the mobile devices, e.g., smartphones and tablet computers, have an operating system installed, and we can improve their functions by downloading any applications on the Web. Then, in order to realize this basic idea, development of an application for the mobile devices is investigated through some computer simulations on the standard desktop PC in this paper. As a result, it is found that i) a developed feature map is useful to identify some candidate topics, ii) a touchscreen is suitable to show the feature map, and iii) arrangement of the feature map can be modified based on our interests. Then, it is concluded that the proposed idea seems to be applicable, even though further consideration is required to brush it up.

近年提案された仮想磁場漸弱法とは，ホップフィールドネットワークとスピングラス理論の類似性に着目した組み合わせ最適化問題の新しい解探索法である．これは，外部磁場を徐々に弱めることで安定なスピン配列を実現するという物理学世界の思考実験をホップフィールドネットワーク世界に導入したもので，対応するニューロン閾値を仮想的な磁場パラメータとみなして制御し，最適解を求めようとする非常に簡便な手法である．先行研究によれば，仮想磁場パラメータの導入で正答率が改善するとの報告があるものの，その極性反転（負値→正値あるいは正値→負値）が重要であるとの指摘もあり，これまでのところ，その詳細については不明なところが多い．そこで本論文では，これまでの経緯を含めて問題点を整理したうえで，Nクイーン問題やナンバー・プレイス問題を取り上げ，さらに複数の仮想磁場パラメータ設定法を用意して，その検証を行った．その結果，いずれの課題においても，仮想磁場パラメータの極性反転が正答率改善に結び付いていることを確認し，その有効性を明らかにした．

A Hopfield network is one of the famous neural network models proposed in 1980s, and it is known as a good tool for solving combinatorial optimization problems. Its working mechanismis quite easy to understand, because its state transition is carried out to reduce the energy defined in advance. But it is true that there are some drawbacks. One is the existence of local energyminima corresponding to spurious solutions. Another is a size of the given task. Generally speaking, it is said that a large-scale network shows poor performance compared with a small-scale one, because the number of combinations for all possibilities are larger. In order to overcome the latter issue, an idea of partitioning applied constraints is tried in this study. Its key aspect is as follows: i) all constraints are divided into several groups, and ii) some of them are applied iteratively while the Hopfield network is searching an optimal solution. As a result of some computer simulations, it is found that the proposed method shows a better score than the conventional method.

An Elman-type feedback SOM (EFSOM) is a modified version of the standard SOM for temporal signal processing. It was applied to various kinds of tasks so far, and it showed good performance on temporal signal processing. By the way, one of the major features inspired by the standard SOM is to visualize given data structure into the two-dimensional plane preserving its topology. Then, from the visualization point of view, a working mechanism of the feedback SOM (FSOM), which is an essential part of the EFSOM, is investigated in this paper. As a result of computer simulations, a trajectory of the winner neurons is bifurcated, not overlapped between any two segments, with the help of feedback pathways. This fact implies that the FSOM can deal with the past history, i.e., the context information, appropriately. Furthermore, when continuous pattern is used for training, it is found that signal processing developed in the SOM is quite similar to that for an A/D converter based on the discretized reference vectors.

In general, a biological nervous system consists of two major parts, i.e., a motor control subsystem and a sensory reception subsystem, and they work together cooperatively as direct-inverse transformation. Paying attention to this bi-directional computing manner, it is essential to perform various kinds of complex activities. Also, it must be important in most application-oriented tasks. In order to confirm its effectiveness, a bi-directional computing architecture inspired from above-mentioned scheme is constructed and applied to time series prediction tasks. At that time, one subsystem in the bi-directional model is assigned to ordinary future prediction (present→future), while the other is to past prediction (present→past) newly introduced in this study. As a result of computer simulations, it is clear that the proposed bi-directional computing architecture shows better performance than the conventional uni-directional one.

Numerous studies on time series prediction have been undertaken by a variety of researchers. Most of them typically used unidirectional computation flow, that is, present signals are applied to the model as an input and predicted future signals are derived from the model as an output. On the contrary, bidirectional computation style has been proposed recently and applied to prediction tasks. A bidirectional neural network model consists of two mutually connected subnetworks and performs direct and inverse transformations bidirectionally. To apply this model to time series prediction tasks, one subnetwork is trained a conventional future prediction task and the other is trained an additional task for past prediction. Since the coupling effects between the future and past prediction subsystems promote the model's signal processing ability, bidirectionalization of the computing architecture makes it possible to improve its performance. Furthermore, in order to investigate the acquired signal transformation, two kinds of chaotic time series—the Mackey–Glass time series and “Data Set A”—are adopted in this paper. As a result of computer simulations, it has been found experimentally that the direct and inverse transformations developed independently and their information integration give the bidirectional model an advantage over the unidirectional one. © 2003 Wiley Periodicals, Inc. Electr Eng Jpn, 145(3): 50–60, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.10232

An Elman-type feedback SOM (EFSOM) is a revised version of the standard SOM for dealing with time-variant information. In order to estimate its performance, an on-line character recognition task is tried with a large-scale training data set in this paper. At the same time, an idea for increasing the number of firing neurons in the competitive layer is examined to improve its trainability by means of enriching the state information. After the EFSOM is trained successfully, some validation tests for spatial displacement and temporal elasticity are also investigated. As a result of computer simulations, it is found that the EFSOM shows good performance and has good temporal signal processing ability.

A virtual magnetic diminuendo method proposed recently is originally inspired by the analogy between the Hopfield network and the spin glass. It is a simple and ingenious idea for solving combinatorial optimization problems, because only a threshold of Hopfield network is controlled from a negative value to zero as a magnetic parameter, which is newly introduced in this study. According to the preliminary study, it seems to be clear experimentally that the proposed method is effective. In order to carry out further considerations, a scheduling function of the virtual magnetic parameter is investigated in this study. As a result of some computer simulations with the crossbar switch problem, it is found that changing polarity (negative i¾? positive) of the magnetic parameter must be effective to improve the score.

A bi-directional computing architecture for time series prediction, which computes not only the future prediction transformation but also the past prediction one, is proposed recently and applied to several prediction tasks. According to the previous studies, an improvement of the prediction performances has been observed with different kinds of data sets. Nevertheless, its detailed mechanism for temporal signal processing is not clear yet. Then, in order to solve this problem, the model's responses are investigated based on the principal component analysis approach in this paper. As a result, it is found experimentally that an enrichment of the inner information representations gives the model an advantage on signal processing abilities through bi-directionalization of the computing architecture.

A number of neural network models and training procedures for time series prediction have been proposed in the technical literature. These models studied for different time-variant data sets have typically used uni-directional computation flow or its modifications. In this study, on the contrary, the concept of bi-directional computational style is proposed and applied to prediction tasks. A bi-directional neural network model consists of two subnetworks performing two types of signal transformations bi-directionally. The networks also receive complementary signals from each other through mutual connections. The model not only deals with the conventional future prediction task, but also with the past prediction, an additional task from the viewpoint of the conventional approach. An improvement of the performance is achieved through making use of the future-past information integration. Since the coupling effects help the proposed model improve its performance, it is found that the prediction score is better than with the traditional uni-directional method. The bi-directional predicting architecture has been found to perform better than the conventional one when tested with standard benchmark sunspots data.