Computational Power of Asynchronously Tuned Automata Enhancing the Unfolded Edge of Chaos.

Asynchronously tuned elementary cellular automata (AT-ECA) are described with respect to the relationship between active and passive updating, and that spells out the relationship between synchronous and asynchronous updating. Mutual tuning between synchronous and asynchronous updating can be interpreted as the model for dissipative structure, and that can reveal the critical property in the phase transition from order to chaos. Since asynchronous tuning easily makes behavior at the edge of chaos, the property of AT-ECA is called the unfolded edge of chaos. The computational power of AT-ECA is evaluated by the quantitative measure of computational universality and efficiency. It shows that the computational efficiency of AT-ECA is much higher than that of synchronous ECA and asynchronous ECA.

Breaking of the Trade-Off Principle between Computational Universality and Efficiency by Asynchronous Updating.

Although natural and bioinspired computing has developed significantly, the relationship between the computational universality and efficiency beyond the Turing machine has not been studied in detail. Here, we investigate how asynchronous updating can contribute to the universal and efficient computation in cellular automata (CA). First, we define the computational universality and efficiency in CA and show that there is a trade-off relation between the universality and efficiency in CA implemented in synchronous updating. Second, we introduce asynchronous updating in CA and show that asynchronous updating can break the trade-off found in synchronous updating. Our finding spells out the significance of asynchronous updating or the timing of computation in robust and efficient computation.

Robotic action acquisition with cognitive biases in coarse-grained state space.

Some of the authors have previously proposed a cognitively inspired reinforcement learning architecture (LS-Q) that mimics cognitive biases in humans. LS-Q adaptively learns under uniform, coarse-grained state division and performs well without parameter tuning in a giant-swing robot task. However, these results were shown only in simulations. In this study, we test the validity of the LS-Q implemented in a robot in a real environment. In addition, we analyze the learning process to elucidate the mechanism by which the LS-Q adaptively learns under the partially observable environment. We argue that the LS-Q may be a versatile reinforcement learning architecture, which is, despite its simplicity, easily applicable and does not require well-prepared settings.

Multilayered neural network with structural lateral inhibition for incremental learning and conceptualization.

Distributed connectionist networks have difficulty learning incrementally because the representations in the network overlap. Therefore, it is necessary to reduce the overlaps of representations for incremental learning. At the same time, the representational overlaps give these networks the ability to generalize. In this study, we use a modified multilayered neural network to numerically examine the trade-off between incremental learning and generalization abilities, and then we propose a novel network model with structural lateral inhibitions to reconcile the two abilities. We also analyze the behavior of the proposed model using Formal Concept Analysis, which reveals that the network implements "conceptualization": differentiation and meditation between intensional and extensional representations. This study suggests a new paradigm for the traditional question, whether representations in the brain are distributed or not.

Cognitively inspired reinforcement learning architecture and its application to giant-swing motion control.

Many algorithms and methods in artificial intelligence or machine learning were inspired by human cognition. As a mechanism to handle the exploration-exploitation dilemma in reinforcement learning, the loosely symmetric (LS) value function that models causal intuition of humans was proposed (Shinohara et al., 2007). While LS shows the highest correlation with causal induction by humans, it has been reported that it effectively works in multi-armed bandit problems that form the simplest class of tasks representing the dilemma. However, the scope of application of LS was limited to the reinforcement learning problems that have K actions with only one state (K-armed bandit problems). This study proposes LS-Q learning architecture that can deal with general reinforcement learning tasks with multiple states and delayed reward. We tested the learning performance of the new architecture in giant-swing robot motion learning, where uncertainty and unknown-ness of the environment is huge. In the test, the help of ready-made internal models or functional approximation of the state space were not given. The simulations showed that while the ordinary Q-learning agent does not reach giant-swing motion because of stagnant loops (local optima with low rewards), LS-Q escapes such loops and acquires giant-swing. It is confirmed that the smaller number of states is, in other words, the more coarse-grained the division of states and the more incomplete the state observation is, the better LS-Q performs in comparison with Q-learning. We also showed that the high performance of LS-Q depends comparatively little on parameter tuning and learning time. This suggests that the proposed method inspired by human cognition works adaptively in real environments.