Gürsel Serpen

Learn More
A small subset of machine learning algorithms, mostly inductive learning based, applied to the KDD 1999 Cup intrusion detection dataset resulted in dismal performance for user-to-root and remote-to-local attack categories as reported in the recent literature. The uncertainty to explore if other machine learning algorithms can demonstrate better performance(More)
A large set of machine learning and pattern classification algorithms trained and tested on KDD intrusion detection data set failed to identify most of the user-toroot and remote-to-local attacks, as reported by many researchers in the literature. In light of this observation, this paper aims to expose the deficiencies and limitations of the KDD data set to(More)
A trainable recurrent neural network, Simultaneous Recurrent Neural network, is proposed to address the scaling problem faced by neural network algorithms in static optimization. The proposed algorithm derives its computational power to address the scaling problem through its ability to "learn" compared to existing recurrent neural algorithms, which are not(More)
This paper explores feasibility of employing the non-recurrent backpropagation training algorithm for a recurrent neural network, Simultaneous Recurrent Neural network, for static optimisation. A simplifying observation that maps the recurrent network dynamics, which is configured to operate in relaxation mode as a static optimizer, to feedforward network(More)
This paper proposes an innovative enhancement of the classical Hopfield network algorithm (and potentially its stochastic derivatives) with an “adaptation mechanism” to guide the neural search process towards high-quality solutions for large-scale static optimization problems. Specifically, a novel methodology that employs gradient-descent in the error(More)
  • Jeffrey A. Geib, Gürsel Serpen
  • 2004 IEEE International Joint Conference on…
  • 2004
This work explores the computational promise of enhancing Simultaneous recurrent neural networks with a stochastic search mechanism as static optimizers. Successful application of simultaneous recurrent neural networks to static optimization problems, where the training had been achieved through one of a number of deterministic gradient descent algorithms(More)
This paper describes a semi-automated procedure for analyzing single photon emission computed tomography (SPECT) images of a human heart and classifying the images into one of several categories: normal, infarct, ischemia, infarct and ischemia, reverse re-distribution, artifact and equivocal. The procedure aids the physician in the interpretation of SPECT(More)
A theorem which establishes the solutions of a given optimization problem as stable points in the state space of single-layer relaxation-type recurrent neural networks is proposed. This theorem establishes the necessary conditions for the neural network to converge to a solution by proposing certain values for the constraint weight parameters of the(More)
A new trainable and recurrent neural optimization algorithm, which has potentially superior capabilities compared to existing neural search algorithms to compute high quality solutions of static optimization problems in a computationally efficient manner, is studied. Specifically, local stability analysis of the dynamics of a relaxation-based recurrent(More)
This paper aims to demonstrate that knowledge-based hybrid learning algorithms are positioned to offer better performance in comparison with purely empirical machine learning algorithms for the automatic classification task associated with the diagnosis of a medical condition described as pulmonary embolism (PE). The main premise is that there exists(More)