Search

In this letter, we attempt to quantify the significance of increasing the number of neurons in the hidden layer of a feedforward neural network architecture using the singular value decomposition (SVD). Through this, we extend some well-known properties of the SVD in evaluating the generalizability of single hidden layer feedforward networks (SLFNs) with respect to the number of hidden layer neurons. The generalization capability of the SLFN is measured by the degree of linear independency of the patterns in hidden layer space, which can be indirectly quantified from the singular values obtained from the SVD, in a postlearning step. A pruning/growing technique based on these singular values is then used to estimate the necessary number of neurons in the hidden layer. More importantly, we describe in detail properties of the SVD in determining the structure of a neural network particularly with respect to the robustness of the selected model.

Numerous power utilities have installed advanced distributed temperature sensing (DTS) systems to measure the temperature of underground cables. This paper presents a general procedure for real-time assessment of underground cable ratings based on DTS. After the identification and location of hot spots on a cable, the cable installation data, load, and DTS-recorded temperature over a period of time are used to estimate soil thermal parameters and assess cable ratings under normal and over-loading conditions. In order to accurately estimate soil thermal parameters, a combined technique of the finite-element method and gradient-based optimization is used. The technique was validated in the laboratory and applied to a rating assessment of a 230-kV/500-MVA cable circuit. The assessed continuous and emergency ratings are helpful in improving the operation of this circuit. Index Terms--Cable rating, distributed temperature sensing, finite-element method (FEM), hot spot, optimization method.

The additive recurrent network structure of linear threshold neurons represents a class of biologically-motivated models, where nonsaturating transfer functions are necessary for representing neuronal activities, such as that of cortical neurons. This paper extends the existing results of dynamics analysis of such linear threshold networks by establishing new and milder conditions for boundedness and asymptotical stability, while allowing for multistability. As a condition for asymptotical stability, it is found that boundedness does not require a deterministic matrix to be symmetric or possess positive off-diagonal entries. The conditions put forward an explicit way to design and analyze such networks. Based on the established theory, an alternate approach to study such networks is through permitted and forbidden sets. An application of the linear threshold (LT) network is analog associative memory, for which a simple design method describing the associative memory is suggested in this paper. The proposed design method is similar to a generalized Hebbian approach, but with distinctions of additional network parameters for normalization, excitation and inhibition, both on a global and local scale. The computational abilities of the network are dependent on its nonlinear dynamics, which in turn is reliant upon the sparsity of the memory vectors. Index Terms--Associative memory, continuous real-valued patterns, dynamics analysis, linear threshold (LT) network.

This paper presents a new approach of task-oriented developmental learning for humanoid robots. It is capable of setting up multiple tasks representation automatically using real-time experiences, thereby enabling a robot to handle various tasks concurrently without the need of predefining the tasks. In the approach, an evolvable partitioned tree structure is used for task representation knowledgebase that is partitioned into different task domains. The search/update of task knowledge is focused on a particular task branch, without considering the whole task knowledgebase that is often large and time consuming in the process. A prototype of the proposed task-oriented developmental learning is designed and implemented using a Khepera robot. Experimental results show that the robot can redirect itself to new tasks through interactions with the environment, and a learned task can be easily updated in order to meet varying specifications in the real world. Index Terms--Humanoid robots, learning systems, task representation.

Multistable networks have attracted much interest in recent years, since multistability is of primary importance for some applications of recurrent neural networks where monostability exhibits some restrictions. This paper focuses on the analysis of dynamical property for a class of additive recurrent neural networks with nonsaturating linear threshold transfer functions. A milder condition is derived to guarantee the boundedness and global attractivity of the networks as compared to that presented in [6]. Dynamical properties of the equilibria of two-dimensional networks are analyzed theoretically, and the relationships between the equilibria features and network parameters (synaptic weights and external inputs) are revealed. In addition, the sufficient and necessary conditions for coexistence of multiple equilibria are obtained, which confirmed the observations in [14] with a cortex-inspired silicon circuit. The results obtained in this paper are applicable to both symmetric and nonsymmetric networks. Simulation examples are used to illustrate the theory developed in this paper. Index Terms--Equilibria, global attractivity, linear threshod (LT) neural network, nonsaturating, multistability.

Parameter setting is a critical step in the Hopfield networks solution of the traveling salesman problem (TSP), which is often prone to extraneous solutions. This paper presents some stability criteria that ensure the convergence of valid solutions and suppression of infeasible solutions. Our theory is based on an enhanced parametric formulation that maps TSP onto a continuous-time Hopfield network (CHN), which is more advantageous than the Hopfield-Tank (H-T) formulation. A set of analytical conditions for optimal parameter settings of the CHN is then derived, and the resulting performance is validated by simulations. Index Terms--Hopfield neural networks, traveling salesman problem (TSP), parameter setting, stability.

This letter presents a new dynamical optimal learning (DOL) algorithm for three-layer linear neural networks and investigates its generalization ability. The optimal learning rates can be fully determined during the training process. The mean squared error (muse) is guaranteed to be stably decreased and the learning is less sensitive to initial parameter settings. The simulation results illustrate that the proposed DOL algorithm gives better generalization performance and faster convergence as compared to standard error back propagation algorithm. Index Terms--Back propagation, dynamical optimal learning (DOL), feedforward neural networks (FNN), stability.

The major drawbacks of the Hopfield network when it is applied to some combinatorial problems, e.g., the traveling salesman problem (TSP), are invalidity of the obtained solutions, trial-and-error setting value process of the network parameters and low-computation efficiency. This letter presents a columnar competitive model (CCM) which incorporates winner-takes-all (WTA) learning rule for solving the TSP. Theoretical analysis for the convergence of the CCM shows that the competitive computational neural network guarantees the convergence to valid states and avoids the onerous procedures of determining the penalty parameters. In addition, its intrinsic competitive learning mechanism enables a fast and effective evolving of the network. The simulation results illustrate that the competitive model offers more and better valid solutions as compared to the original Hopfield network. Index Terms--Convergence analysis, Hopfield networks, traveling salesman problem (TSP), winner-takes-all (WTA).