Due to the influence of the complex marine environment, the marine target detection based
on statistical theory is difficult to achieve high-performance. Moreover, due to various targets' …

In this paper, we exploit the adaptive stochastic resonance effect in the convolutional neural
network with threshold activation functions for enabling the back-propagation gradient …

This paper proposes a flexible probabilistic activation function that enhances the training
and operation of artificial neural networks by intentionally injecting noise to gain additional …

Aiming to ensure the feasibility of the backpropagation training of feedforward threshold
neural networks, each hidden unit layer is designed to be composed of a sufficiently large …

Hard-threshold nonlinearities are of significant interest for neural-network information
processing due to their simplicity and low-cost implementation. They however lack an …

Using a gradient-based algorithm, we investigate signal estimation and filtering in a large-
scale summing network of single-bit quantizers. Besides adjusting weights, the proposed …

Threshold neural networks are highly useful in engineering applications due to their ease of
hardware implementation and low computational complexity. However, such threshold …

In this paper, we investigate the noise benefits to maximum likelihood type estimators (M-
estimator) for the robust estimation of a location parameter. Two distinct noise benefits are …

For a weak signal buried in a given background noisy environment, a generalized matched
filter composed of nonlinearities and weight coefficients is investigated by exploring the …

This paper investigates the benefits of intentionally adding noise to a Bayesian estimator,
which comprises a linear combination of a number of individual Bayesian estimators that are …