Learning in the recurrent random neural network
Neural Computation
QoSMIC: quality of service sensitive multicast Internet protocol
Proceedings of the ACM SIGCOMM '98 conference on Applications, technologies, architectures, and protocols for computer communication
Learning Algorithms: Theory and Applications in Signal Processing
Learning Algorithms: Theory and Applications in Signal Processing
Learning to Predict by the Methods of Temporal Differences
Machine Learning
A Realizable Model for Stochastic Sequential Machines
IEEE Transactions on Computers
On probabilistic automata with structural restrictions
SWAT '69 Proceedings of the 10th Annual Symposium on Switching and Automata Theory (swat 1969)
A survey of active network research
IEEE Communications Magazine
The Tempest: a framework for safe, resource assured, programmable networks
IEEE Communications Magazine
A programmable transport architecture with QoS guarantees
IEEE Communications Magazine
The IEEE P1520 standards initiative for programmable network interfaces
IEEE Communications Magazine
IEEE Communications Magazine
Protocol boosters: applying programmability to network infrastructures
IEEE Communications Magazine
Safety and security of programmable network infrastructures
IEEE Communications Magazine
Implementing communication protocols in Java
IEEE Communications Magazine
Distributed object technology for networking
IEEE Communications Magazine
Function approximation with spiked random networks
IEEE Transactions on Neural Networks
Introducing new Internet services: why and how
IEEE Network: The Magazine of Global Internetworking
Mobile agents - enabling technology for active intelligent network implementation
IEEE Network: The Magazine of Global Internetworking
ACC: using active networking to enhance feedback congestion control mechanisms
IEEE Network: The Magazine of Global Internetworking
A self-aware approach to denial of service defence
Computer Networks: The International Journal of Computer and Telecommunications Networking
Admission of QoS aware users in a smart network
ACM Transactions on Autonomous and Adaptive Systems (TAAS)
On the use of memory and resources in minority games
ACM Transactions on Autonomous and Adaptive Systems (TAAS)
Adding more intelligence to the network routing problem: AntNet and Ga-agents
Applied Soft Computing
An initiative for a classified bibliography on G-networks
Performance Evaluation
Users and services in intelligent networks
AINTEC'05 Proceedings of the First Asian Internet Engineering conference on Technologies for Advanced Heterogeneous Networks
Random neural networks for the adaptive control of packet networks
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Bibliography on G-networks, negative customers and applications
Mathematical and Computer Modelling: An International Journal
Wireless networks in emergency management
Proceedings of the first ACM international workshop on Practical issues and applications in next generation wireless networks
Large scale simulation for human evacuation and rescue
Computers & Mathematics with Applications
An intelligent routing approach using genetic algorithms for quality graded network
International Journal of Intelligent Systems Technologies and Applications
A QoS-based routing approach using genetic algorithms for bandwidth maximisation in networks
International Journal of Artificial Intelligence and Soft Computing
Strengthening the security of cognitive packet networks
International Journal of Advanced Intelligence Paradigms
Smart data packet ad hoc routing protocol
Computer Networks: The International Journal of Computer and Telecommunications Networking
Hi-index | 0.00 |
We propose packet switching networks in which intelligent capabilities for routing and flow control are concentrated in the packets, rather than in the nodes and protocols. Networks which contain Cognitive Packets (CP) will be called Cognitive Packet Networks. Cognitive packets route themselves. They are assigned goals before entering the network, and pursue these goals adaptively. They learn to avoid congestion and to avoid getting lost or being destroyed. Cognitive packets learn from their own observations about the network and from the experience of other packets with whom they exchange information via mailboxes. Cognitive packets rely minimally on routers, so that network nodes only serve as buffers, mailboxes and processors. Each cognitive packet starts with a given representation of the network from which it then progressively constructs its own Cognitive Map of network state and uses it to make routing decisions. Cognitive packets can belong to classes, so that a class of packets share the same goals, use similar sets of rules, and make use of each other's experience. This paper describes CPN and shows how learning techniques can support the intelligent behavior of Cognitive Packets. Simulation results illustrate the effectiveness of these ideas.