Results 171 to 180 of about 4,010,683 (211)
Some of the next articles are maybe not open access.
ACM Computing Surveys, 1996
We present an overview of current research on artificial neural networks, emphasizing a statistical perspective. We view neural networks as parameterized graphs that make probabilistic assumptions about data, and view learning algorithms as methods for finding parameter values that look probable in the light of the data.
Michael I. Jordan, Christopher M. Bishop
openaire +1 more source
We present an overview of current research on artificial neural networks, emphasizing a statistical perspective. We view neural networks as parameterized graphs that make probabilistic assumptions about data, and view learning algorithms as methods for finding parameter values that look probable in the light of the data.
Michael I. Jordan, Christopher M. Bishop
openaire +1 more source
2009
Neural networks are a class of intelligent learning machines establishing the relationships between descriptors of real-world objects. As optimisation tools they are also a class of computational algorithms implemented using statistical/numerical techniques for parameter estimate, model selection, and generalisation enhancement.
openaire +3 more sources
Neural networks are a class of intelligent learning machines establishing the relationships between descriptors of real-world objects. As optimisation tools they are also a class of computational algorithms implemented using statistical/numerical techniques for parameter estimate, model selection, and generalisation enhancement.
openaire +3 more sources
Proceedings of the 9th annual conference companion on Genetic and evolutionary computation, 2007
Neuroevolution, i.e. evolution of artificial neural networks, has recently emerged as a powerful technique for solving challenging reinforcement learning problems. Compared to traditional (e.g. value-function based) methods, neuroevolution is especially strong in domains where the state of the world is not fully known: The state can be disambiguated ...
openaire +8 more sources
Neuroevolution, i.e. evolution of artificial neural networks, has recently emerged as a powerful technique for solving challenging reinforcement learning problems. Compared to traditional (e.g. value-function based) methods, neuroevolution is especially strong in domains where the state of the world is not fully known: The state can be disambiguated ...
openaire +8 more sources
Neural Computation, 1999
A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN.
Anders Krogh, Søren Kamaric Riis
openaire +3 more sources
A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN.
Anders Krogh, Søren Kamaric Riis
openaire +3 more sources
International Journal of Neural Systems, 2009
Most current Artificial Neural Network (ANN) models are based on highly simplified brain dynamics. They have been used as powerful computational tools to solve complex pattern recognition, function estimation, and classification problems. ANNs have been evolving towards more powerful and more biologically realistic models.
Samanwoy Ghosh-Dastidar, Hojjat Adeli
openaire +3 more sources
Most current Artificial Neural Network (ANN) models are based on highly simplified brain dynamics. They have been used as powerful computational tools to solve complex pattern recognition, function estimation, and classification problems. ANNs have been evolving towards more powerful and more biologically realistic models.
Samanwoy Ghosh-Dastidar, Hojjat Adeli
openaire +3 more sources
IEEE Communications Magazine, 1989
The author argues that a strong impetus for using neural networks is that they provide a framework for designing massively parallel machines. He notes that the highly interconnected architecture of switching networks suggests similarities to neural networks.
openaire +2 more sources
The author argues that a strong impetus for using neural networks is that they provide a framework for designing massively parallel machines. He notes that the highly interconnected architecture of switching networks suggests similarities to neural networks.
openaire +2 more sources
1995
Proper initialization is one of the most important prerequisites for fast convergence of feed-forward neural networks like high order and multilayer perceptrons. This publication aims at determining the optimal value of the initial weight variance (or range), which is the principal parameter of random weight initialization methods for both types of ...
Thimm, Georg, Fiesler, Emile
openaire +1 more source
Proper initialization is one of the most important prerequisites for fast convergence of feed-forward neural networks like high order and multilayer perceptrons. This publication aims at determining the optimal value of the initial weight variance (or range), which is the principal parameter of random weight initialization methods for both types of ...
Thimm, Georg, Fiesler, Emile
openaire +1 more source
A neural network to design neural networks
IEEE Transactions on Circuits and Systems, 1991The design of the Hopfield associative memory is reformulated in terms of a constraint satisfaction problem. An electronic neural net capable of solving this problem in real time is proposed. Circuit solutions correspond to symmetrical zero-diagonal matrices that possess few spurious stable states.
openaire +1 more source
A survey of uncertainty in deep neural networks
Artificial Intelligence Review, 2023Xiao Xiang Zhu, Jianxiang Feng
exaly