Shortcut connections are a popular architectural feature of multi-layer perceptrons. It is generally assumed that by implementing a linear submapping, shortcuts assist the learning process in the remainder of the network. Here we find that this is not always the case: shortcut weights may also act as distractors that slow down convergence and can lead to inferior solutions. This problem can be ...

Gene category testing problems involve testing hundreds of null hypotheses that correspond to nodes in a directed acyclic graph. The logical relationships among the nodes in the graph imply that only some configurations of true and false null hypotheses are possible and that a test for a given node should depend on data from neighboring nodes. We developed a method based on a hidden Markov mode...

In this paper, we investigate random linear network coding (RLNC) in practical wireless networks. First we apply RLNC in the legacy network (wireless LAN mesh network) of multiple unicasts by the global RLNC. In the simulation results, in the system with the global RLNC, the network load and the power consumption is reduced for the simple topologies. However, the global RLNC cannot be applied t...

In this paper we consider the problem of approximating functions from noisy data. We propose an incremental supervised learning algorithm for RBF networks. Hidden gaussian nodes are added in an iterative manner during the training process. For each new node added, the activation function center and the output connection weight are settled according to an extended chained version of the Nadaraja...

Radial Basis Function neural network (RBFNN) is a combination of learning vector quantizer LVQ-I and gradient descent. RBFNN is first proposed by (Broomhead & Lowe, 1988), and their interpolation and generalization properties are thoroughly investigated in (Lowe, 1989), (Freeman & Saad, 1995). Since the mid-1980s, RBFNN has been used to apply on many applications, such as pattern classification...

Evolutionary artiicial neural networks (EANNs) refer to a special class of artiicial neural networks (ANNs) in which evolution is another fundamental form of adaptation in addition to learning. The evolution in EANNs is often simulated by genetic algorithms (GAs), evolutionary programming (EP), or other evolutionary algorithms. This paper describes an EP-based EANNs which learn both their weigh...

This paper considers the identification problem of network structures interconnected dynamical systems using measured output data. In particular, we propose an method based on data each node in whose dynamic is unknown. The proposed consists three steps: first consider outputs nodes to be all states dynamics nodes, and unmeasurable hidden inputs with unknown dynamics. second step, define as new...

While routing in multi-hop packet radio networks (static Ad-hoc wireless networks), it is crucial to minimize power consumption since nodes are powered by batteries of limited capacity and it is expensive to recharge the device. This paper studies the problem of broadcast routing in radio networks. Given a network with an identified source node, any broadcast routing is considered as a directed...