http://popups.lib.uliege.be/1373-5411/index.php?id=183 Index terms fr 0 http://popups.lib.uliege.be/1373-5411/index.php?id=1118 In this paper we present the implementation of control structures of a high-level concurrent programming language into the machine level of analog recurrent neural nets. Neural nets can thus perform high-level symbolic tasks, together with their reputed subsymbolic learning capabilities. We emphasize the construction of neural software capable of integrating both learning and programmed control modules. Fri, 05 Jul 2024 13:45:06 +0200 Thu, 10 Oct 2024 16:31:24 +0200 http://popups.lib.uliege.be/1373-5411/index.php?id=1118 http://popups.lib.uliege.be/1373-5411/index.php?id=182 Dissipative flows model a large variety of physical systems. In this paper the evolution of such systems is interpreted as a process of computation ; the attractor of the dynamics represents the output. A framework for an algorithmic analysis of dissipative flows is presented, enabling the comparison of the performance of discrete and continuous time analog computation models. A simple algorithm for finding the maximum of n numbers is analyzed, and shown to be highly efficient. The notion of tractable (polynomial) computation in the Turing model is conjectured to correspond to computation with tractable (analytically solvable) dynamical systems having polynomial complexity. Wed, 19 Jun 2024 11:05:20 +0200 Wed, 19 Jun 2024 11:05:27 +0200 http://popups.lib.uliege.be/1373-5411/index.php?id=182