As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
We add a mobility functionality to the neurons of an artificial neural network as a key expression of their intentionality of cooperating in the overall computational task of the network. We draw the main features of this functionality from mobility models developed in some macroscale biological frameworks. The goal is to improve the learning capability of the network. The main tools are a mutual positioning strategy that may be shared with other kinds of social communities and a unifying framework where the physical and cognitive aspects of the mobility are dealt with synergistically. The new connectionist paradigm we introduce is susceptible of overriding many of the current methodologies and drawbacks affecting the training of neural networks on heavy problems, including those concerning the exploitation of deep architectures. We test our network of mobile neurons on a pair of well-known benchmarks, showing interesting performances and opening further problems.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.