Improved neural heuristics for multicast routing

We focus on Erol Gelenbe's scientific and technical contributions to probability models in the computer and information sciences, but limit our survey to the last fifteen years. We start with a brief overview of his work as a single author, as well as his work in collaboration with over 200 co-authors. We discuss some of his recent and innovative work regarding a new probability model that represents Intermittent Energy Sources for Computing and Communications, introducing Energy Packet Networks which are a probabilistic representation of the flow, storage and consumption of electrical energy at the microscopic level (in electronic chips), and at the macroscopic level (e.g. in buildings or data centers) and for its routing and dynamic usage by consuming units (such as computer elements, chips or machines). We next discuss his work on designing computer and communication systems that parsimoniously use energy in order to achieve a satisfactory level of quality of service (QoS). Trade-offs between system QoS and energy consumption are also considered. Then we turn to Prof. Gelenbe's pioneering work on Autonomic Communications and the design and implementation of CPN, the Cognitive Packet Network, and we also briefly review his spiking random neural network that was used in CPN. This is followed by a brief review of work that he conducted since 1999 on human evacuation from dangerous or catastrophic environments, and the design of technology driven Emergency Management Systems. His research since the late 2000s on Gene Regulatory Networks is then covered together with its application to the detecting possible disease from microarray data. Finally, we briefly discuss some novel analytical models that he developed in this period with publications appearing in journals of physics and applied mathematics.

Section: The Random Neural Networkmentioning

confidence: 99%

Erol Gelenbe: A Career in Multi-Disciplinary Probability Models

Caglayan¹

2016

“…Other applications of the random neural network that do not require learning include function optimization (Gelenbe, Koubi, and Pekergin [99]) and texture generation (Atalay and Gelenbe [9], Atalay, Gelenbe, and Yalabik [10]). Applications of the RNN were published for video compression (Cramer, Gelenbe, and Bakircioglu [20,21]), complex recognition tasks (Abdelbaki, Gelenbe, and El-Khamy [1], Abdelbaki, Gelenbe, and Kocak [2], Abdelbaki et al [3], Aguilar and Gelenbe [8], Gelenbe, Ghanwani, and Srinivasan [85], Hocaoglu et al [155]), and to the sensory search of patterns and objects (Gelenbe and Cao [74], Gelenbe and Koçak [97], Gelenbe, Koçak, and Wang [98]). A polynomial time-complexity learning algorithm for RNNs having soma-to-soma interactions was first presented in (Gelenbe and Timotheou [142]) and is further developed in (Wang and Gelenbe [184]).…”

Section: Extensions and Applications Of The Random Neural Network (Rnn)mentioning

confidence: 99%

G-Networks and Their Applications to Machine Learning, Energy Packet Networks and Routing: Introduction to the Special Issue

Caglayan¹

2017

This paper introduces a special issue of this journal (Probability in the Engineering and Informational Sciences) that is devoted to G(elenbe)-Networks and their Applications. The special issue is based on revised versions of some of the papers that were presented at a workshop held in early January 2017 at the Séminaire Saint-Paul in Nice (France). It includes contributions in several research directions that followed from the introduction of the G-Network in the late 1980s. The papers present original theoretical developments, as well as applications of G-Networks to Machine Learning, to the performance optimization of energy systems via the novel Energy Packet Networks formalism for systems that operate with renewable and intermittent energy sources, and to packet network routing and Cloud management over the Internet. We introduce these contributions from the perspective of an overview of recent work based on G-Networks.

“…In this way, an appropriate region for the optimal step-size is identified; then, a divide and conquer procedure is followed to find the largest value β m satisfying Eq. (24).…”

Section: Projected Gradient Non-negative Least-squares Algorithmmentioning

confidence: 99%

“…RNN has attracted a lot of attention in the scientific community due to its analytical solvability, excellent learning capacity, implementation ease, as well as its representational, modeling and universal approximation capabilities [19]. RNN has also been applied for the solution for different types of problems including optimization (e.g., minimum Steiner tree [24], assignment of assets to tasks under uncertainty [31], task assignment in distributed systems [2], rescuer assignment of emergency evacuation [25], cognitive packet networks [28]) and modeling (e.g., G-networks [3,18,20,22], gene regulatory networks [23], and protein interaction networks [42]) problems. Nonetheless, the most important application area of RNN regards the solution of supervised learning problems such as laser intensity vehicle classification [35], wafer surface reconstruction [27], mine detection [1] and denial-of-service attack detection [41].…”

Section: Introductionmentioning

confidence: 99%

Fast Non-Negative Least-Squares Learning in the Random Neural Network

Timotheou

2016

The random neural network is a biologically inspired neural model where neurons interact by probabilistically exchanging positive and negative unit-amplitude signals that has superior learning capabilities compared to other artificial neural networks. This paper considers non-negative least squares supervised learning in this context, and develops an approach that achieves fast execution and excellent learning capacity. This speedup is a result of significant enhancements in the solution of the non-negative least-squares problem which regard (a) the development of analytical expressions for the evaluation of the gradient and objective functions and (b) a novel limited-memory quasi-Newton solution algorithm. Simulation results in the context of optimizing the performance of a disaster management problem using supervised learning verify the efficiency of the approach, achieving two orders of magnitude execution speedup and improved solution quality compared to state-of-the-art algorithms.