Various kinds of content replication strategies in pure P2P networks have recently been examined. However, such strategies have not been thoroughly considered in hybrid P2P networks. In a hybrid P2P network, the target content can easily be found because there is a server that controls each peer and its content. Therefore, it is important to decrease futile storage resource consumption, since the data search cost through the network is relatively small. This paper proposes an effective content replication strategy that takes into account storage capacity restrictions. In brief, this method restricts the number of contents replicas possessed by a peer using threshold-based control by relocating or deleting excess replicas. Furthermore, the effectiveness of the proposal is evaluated using computer simulations.

Data Replication can be used to improve the system availability of distributed systems. In such a system, a mechanism is required to maintain the consistency of the replicated data. The grid structure technique based on quorum is one of the solutions to perform this while providing a high availability of the system. It was shown in the study that, it still requires a bigger number of copies be made available to construct a quorum. So it is not suitable for large systems. In this paper, we propose a technique called the neighbor replication on grid (NRG) technique by considering only neighbors to have the replicated data. In comparison to the grid structure technique, NRG requires a lower communication cost for an operation, while providing a higher system availability, which is preferred for large systems.

An associative memory model with a forgetting process a la Mezard et al. is investigated for a piecewise nonmonotonic output function by the SCSNA proposed by Shiino and Fukai. Similar to the formal monotonic two-state model analyzed by Mezard et al. , the discussed nonmonotonic model is also free from a catastrophic deterioration of memory due to overloading. We theoretically obtain a relationship between the storage capacity and the forgetting rate, and find that there is an optimal value of forgetting rate, at which the storage capacity is maximized for the given nonmonotonicity. The maximal storage capacity and capacity ratio (a ratio of the storage capacity for the conventional correlation learning rule to the maximal storage capacity) increase with nonmonotonicity, whereas the optimal forgetting rate decreases with nonmonotonicity.

We apply evolutionary algorithms to neural network model of associative memory. In the model, some of the appropriate configurations of the synaptic weights allow the network to store a number of patterns as an associative memory. For example, the so-called Hebbian rule prescribes one such configuration. However, if the number of patterns to be stored exceeds a critical amount (over-loaded), the ability to store patterns collapses more or less. Or, synaptic weights chosen at random do not have such an ability. In this paper, we describe a genetic algorithm which successfully evolves both the random synapses and over-loaded Hebbian synapses to function as associative memory by adaptively pruning some of the synaptic connections. Although many authors have shown that the model is robust against pruning a fraction of synaptic connections, improvement of performance by pruning has not been explored, as far as we know.

In this paper, dependence of storage capacity of an analogue associative memory model using nonmonotonic neurons on static synaptic noise and static threshold noise is shown. This dependence is analytically calculated by means of the self-consistent signal-to-noise analysis (SCSNA) proposed by Shiino and Fukai. It is known that the storage capacity of an associative memory model can be improved markedly by replacing the usual sigmoid neurons with nonmonotonic ones, and the Hopfield model has theoretically been shown to be fairly robust against introducing the static synaptic noise. In this paper, it is shown that when the monotonicity of neuron is high, the storage capacity decreases rapidly according to an increase of the static synaptic noise. It is also shown that the reduction of the storage capacity is more sensitive to an increase in the static threshold noise than to the increase in the static synaptic noise.

Typical concepts concerning memorizing capability of multilayer neural networks are statistical capacity and Vapnik-Chervonenkis (VC) dimension. These are differently defined each other according to intended applications. Although for the VC dimension several tighter upper bounds have been proposed, even if limited to networks with linear threshold elements, in literature, upper bounds on the statistical capacity are available only by the order of magnitude. We argue first that the proposed or ordinary formulation of the upper bound on the statistical capacity depends strongly on, and thus, it is possibly expressed by the number of the first hidden layer units. Then, we describe a more elaborated upper bound of the memorizing capacity of multilayer neural networks with linear threshold elements, which improves former results. Finally, a discussion of gaining good generalization is presented.