Sciweavers

265 search results - page 3 / 53
» On the Computational Power of Neural Nets
Sort
View
ESANN
2008
13 years 9 months ago
Petri nets design based on neural networks
Petri net faulty models are useful for reliability analysis and fault diagnosis of discrete event systems. Such models are difficult to work out as long as they must be computed ac...
Edouard Leclercq, Souleiman Ould el Medhi, Dimitri...
AB
2008
Springer
14 years 1 months ago
Neural Algebra and Consciousness: A Theory of Structural Functionality in Neural Nets
Abstract. Thoughts are spatio-temporal patterns of coalitions of firing neurons and their interconnections. Neural algebras represent these patterns as formal algebraic objects, a...
Erwin Engeler
EUROCAST
1997
Springer
85views Hardware» more  EUROCAST 1997»
13 years 11 months ago
Turing Universality of Neural Nets (Revisited)
We show how to use recursive function theory to prove Turing universality of finite analog recurrent neural nets, with a piecewise linear sigmoid function as activation function. W...
João Pedro Guerreiro Neto, Hava T. Siegelma...
LICS
2012
IEEE
11 years 9 months ago
The Ordinal-Recursive Complexity of Timed-arc Petri Nets, Data Nets, and Other Enriched Nets
—We show how to reliably compute fast-growing functions with timed-arc Petri nets and data nets. This construction provides ordinal-recursive lower bounds on the complexity of th...
Serge Haddad, Sylvain Schmitz, Philippe Schnoebele...
NECO
2006
60views more  NECO 2006»
13 years 7 months ago
On the Computational Power of Threshold Circuits with Sparse Activity
Circuits composed of threshold gates (McCulloch-Pitts neurons, or perceptrons) are simplified models of neural circuits with the advan1
Kei Uchizawa, Rodney J. Douglas, Wolfgang Maass