Dragos Calitoiu

Learn More
Traditional pattern recognition (PR) systems work with the model that the object to be recognized is characterized by a set of features, which are treated as the inputs. In this paper, we propose a new model for PR, namely one that involves chaotic neural networks (CNNs). To achieve this, we enhance the basic model proposed by Adachi (Neural Netw 10:83–98,(More)
The usual goal of modeling natural and artificial perception involves determining how a system can extract the object that it perceives from an image that is noisy. The "inverse" of this problem is one of modeling how even a clear image can be perceived to be blurred in certain contexts. To our knowledge, there is no solution to this in the literature other(More)
The Hodgkin-Huxley (HH) neuron is a nonlinear system with two stable states: A fixed point and a limit cycle. Both of them co-exist. The behavior of this neuron can be switched between these two equilibria, namely spiking and resting respectively, by using a perturbation method. The change from spiking to resting is named Spike Annihilation, and the(More)
Various advanced disease-surveillance models have been developed to provide early detection of infectious disease outbreaks and bioterrorist attacks. New methods that increase the overall detection capabilities of these systems can have a broad practical impact. This paper considers the problem of learning the Contagion Parameter (CP) in a black box model(More)
In this paper we address the general question of what is the best strategy to search efficiently for randomly located objects (target sites). We propose a new agent based algorithm for searching in an unpredictable environment. The originality of our work consists in applying a non-cooperative strategy, namely the distributed Goore Game model, as opposed to(More)
The problem of plastic anti-personal mine detection is well known. These devices are typically 75mm in diameter and between 25mm to 50mm in thickness. Some types contain no metal, but their explosive (RDX, TNT) can be considered as a dielectric material with a dielectric constant between 3.5 and 4.0. This electromagnetic property enables a radar to identify(More)
In this paper, we analyze the stability of a model for the self/non-self discrimination. The model simulates how the T helper cells (Th), namely lymphocytes developed in the thymus, learn which antigens are self and which ones are non-self. All antigen-responsive cells are born without effector activity and, in the initial stage, have two pathways open to(More)
Traditional Pattern Recognition (PR) systems work with the model that the object to be recognized is characterized by a set of features, which are treated as the inputs. In this paper, we propose a new model for Pattern Recognition (PR), namely, one that involves Chaotic Neural Networks (CNNs). To achieve this, we enhance the basic model proposed by Adachi(More)