Towards Ubiquitous Intelligent Computing: Heterogeneous Distributed Deep Neural Networks

Intelligent Search for Distributed Information Sources Using Heterogeneous Neural Networks

Intelligent search for distributed information sources using heterogeneous neural networks Book Chapter How to cite: Yang, Hui and Zhang, Minjie (2003). Intelligent search for distributed information sources using heterogeneous neural networks. In: Zhou, Xiaofang; Zhang, Yanchun and Orlowska, Maria E. eds. Web Technologies and Applications, 5th Asian-Pacific Web Conference (APWeb 2003). Lecture...

LOCAL DISTRIBUTED MOBILE COMPUTING SYSTEM FOR DEEP NEURAL NETWORKS by

Towards Evolutionary Deep Neural Networks

This paper is concerned with the problem of optimizing deep neural networks with diverse transfer functions using evolutionary methods. Standard evolutionary (SEDeeNN) and cooperative coevolutionary methods (CoDeeNN) were applied to three different architectures characterized by different constraints on neural diversity. It was found that (1) SEDeeNN (but not CoDeeNN) changes parameters uniform...

Intelligent Software for Ubiquitous Computing

You propably remember that agents was a buzzword in the popular computer science press about five years ago. Now, the commotion has almost silenced. Experience has proven that the some of the visions invented in the craze are diffucult to implement in reality, and people do not want their work to be associated with any of these broken promises. However, I believe that the idea behind agents has...

Deploying Ubiquitous Computing Applications on Heterogeneous Next Generation Networks

This chapter describes a human centric approach for designing and deploying ubiquitous computing applications. These are considered as activity spheres consisting of tasks which must be executed using the resources available in an Ambient Intelligence space. Such resources include objects augmented with embedded ICT components and software modules. An architectural approach and a corresponding ...