Neucom-WNS 2014 : Special Issue on Weightless Neural Systems
Call For Papers
Mimicking biological neurons by focusing on the excitatory/inhibitory decoding, which is naturally performed by the dendritic trees, is a different and attractive alternative to the integrate-and-fire neuron stylization. In such alternative analogy, neurons can be seen as a set of Random Access Memory (RAM) nodes addressed by Boolean inputs and producing Boolean outputs. The shortening of the semantic gap between the synaptic-centric model of the neuron and the dominating binary digital computational environment, is among the interesting benefits of the weightless neural approach.
Weightless Neural Networks (WNNs) are based mainly on networks of Random Access Memory neurons. Like Boolean Neural Networks, they have binary inputs and outputs. However, they do not use the concept of weights between the neurons. Thus, the training process of WNNs is very efficient. Instead of learning via weight adjustments, it simply updates the memory contents of the nodes. The model behind WNNs is very effective as it is demonstrated in many real-word applications, ranging from pattern recognition to artificial consciousness.
The focus of this special issue, to be published in Elsevier Journal on Neurocomputing, will be on novel paradigms and all aspects of efficient system implementations, both in hardware and/or software, which are inspired by WNN. Specific applications of WNN to solve real-world problems as well as review papers are also welcome.
Paper Submission: 28 February 2014;
Decision Notification: 30 June 2014;
Possible revision: 30 August 2014
Camera-Ready Submission: 30 November 2014
If you intend to contribute to this special issue, please send a title and abstract of your contribution to the guest editors.
The submissions will be handled through the Electronic Editorial System of Elsevier. Prospective authors are invited to register at http://ees.elsevier.com/neucom/ and submit their papers electronically in a format consistent with the author submission guidelines of Neurocomputing. When submitting, please indicate that your manuscript is a Special Issue Paper and select the topic Weightless Neural Systems (WNSs), when prompted by the system. For questions regarding submissions to the special issue, please contact one of the guest editors. For technical questions regarding the submission website, please contact the support office at Elsevier or the guest editors.
Electronics Engineering & Telecommunications, State University of Rio de Janeiro – UERJ
Felipe M. G. França
Systems Engineering & Computation, Federal University of Rio de Janeiro - UFRJ
Massimo de Gregorio
Istituto di Cibernetica Eduardo Caianiello – CNR Pozzuoli (NA), Italy
Luiza M. Mourelle
Systems Engineering & Computation, State University of Rio de Janeiro – UERJ