Search

Recently we have proposed a simple circuit of winner-take-all (WTA) neural network. Assuming no external input, we have derived an analytic equation for its network response time. In this paper, we further analyze the network response time for a class of winner-take-all circuits involving self-decay and show that the network response time of such a class of WTA is the same as that of the simple WTA model. Index Terms - Inputless winner-take-all neural network, network response time, self-decay.

An error control scheme for transmitting vector-quantized data over noisy channels is presented. The trellis-coded Kohonen map or TCKM error control transmission system combines the source coder, error control, and modulation in its design. A comparison with the approach based on the self-organizing feature map shows that the TCKM error control transmission system can further control the noise in the received data when the signal-to-noise ratio in the channel falls into a suitable range.

This paper presents an algorithm to form a topographic map resembling to the self-organizing map. The idea stems on defining an energy function which reveals the local correlation between neighboring neurons. The larger the value of the energy function, the higher the correlation of the neighborhood neurons. On this account, the proposed algorithm is defined as the gradient ascent of this energy function. Simulations on two-dimensional maps are illustrated. Index Terms - Kohonen net, neural network, self-organizing map.

In the transmission of vector quantized data, the vector quantizer and the communication system are usually designed separately. With such an approach, the channel noise results in significant degradations in the performance of the vector quantizer. To solve this problem, we should properly create the mapping from the codebook of the quantizer to the channel signal set of the communication system. This paper proposes a new approach to construct such a mapping based on the ordering property of the self-organizing feature map (SOFM). We use the neighborhood structure of the SOFM and the neighborhood structure of the channel signal set to construct the mapping. Simulation results confirm that the proposed approach is robust with respect to channel noise. Index Terms - Noisy channel, self-organizing map, vector quantization.

In this paper, a bidirectional associative memory (BAM) model with second-order connections, namely second-order bidirectional associative memory (SOBAM), is first reviewed. The stability and statistical properties of the SOBAM are then examined. We use an example to illustrate that the stability of the SOBAM is not guaranteed. For this result, we cannot use the conventional energy approach to estimate its memory capacity. Thus, we develop the statistical dynamics of the SOBAM. Given that a small number of errors appear in the initial input, the dynamics shows how the number of errors varies during recall. We use the dynamics to estimate the memory capacity, the attraction basin, and the number of errors in the retrieved items. Extension of the results to higher-order bidirectional associative memories is also discussed. Index Terms - Associative memory, BAM, neural network, stability.

Recursive least squares (RLS)-based algorithms are a class of fast online training algorithms for feedforward multilayered neural networks (FMNNs). Though the standard RLS algorithm has an implicit weight decay term in its energy function, the weight decay effect decreases linearly as the number of learning epochs increases, thus rendering a diminishing weight decay effect as training progresses. In this paper, we derive two modified RLS algorithms to tackle this problem. In the first algorithm, namely, the true weight decay RLS (TWDRLS) algorithm, we consider a modified energy function whereby the weight decay effect remains constant, irrespective of the number of learning epochs. The second version, the input perturbation RLS (IPRLS) algorithm, is derived by requiring robustness in its prediction performance to input perturbations. Simulation results show that both algorithms improve the generalization capability of the trained network. Index Terms--Generalizability of feedforward multilayered neural networks (FMNNs), input perturbation (IP), recursive least squares (RLS) error method, true weight decay (TWD).

A novel method using neural networks for translational invariant object recognition is described in this paper. The objective is to enable the recognition of objects in any shifted position when the objects are presented to the network in only one standard location during the training procedure. With the presence of multiple or overlapped objects in the scene, translational invariant object recognition is a very difficult task. Noise corruption of the image creates another difficulty. In this paper, a novel approach is proposed to tackle this problem, using neural networks with the consideration of multiple objects and the presence of noise. This method utilizes the secondary responses activated by the backpropagation network. A confirmative network is used to obtain the object identification and location, based on these secondary responses. Experimental results were used to demonstrate the ability of this approach. [ABSTRACT FROM AUTHOR]