Results 251 to 260 of about 1,504,339 (298)
Some of the next articles are maybe not open access.
Neural Networks, 2001
Formulations of artificial neural networks are directly related to assumptions about neural coding in the brain. Traditional connectionist networks assume channel-based rate coding, while time-delay networks convert temporally-coded inputs into rate-coded outputs.
openaire +2 more sources
Formulations of artificial neural networks are directly related to assumptions about neural coding in the brain. Traditional connectionist networks assume channel-based rate coding, while time-delay networks convert temporally-coded inputs into rate-coded outputs.
openaire +2 more sources
Communications of the ACM, 2019
Yoshua Bengio, Geoffrey Hinton, and Yann LeCun this month will receive the 2018 ACM A.M. Turing Award for conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing.
openaire +1 more source
Yoshua Bengio, Geoffrey Hinton, and Yann LeCun this month will receive the 2018 ACM A.M. Turing Award for conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing.
openaire +1 more source
2007 IEEE Symposium on Foundations of Computational Intelligence, 2007
We analyze a bivariate marginal distribution genetic model in case of infinite populations and provide relations between the associated infinite population genetic system and the neural networks. A lower bound on population size is exhibited stating that the behaviour of the finite population system, in case of sufficiently large sizes, can be suitably
openaire +1 more source
We analyze a bivariate marginal distribution genetic model in case of infinite populations and provide relations between the associated infinite population genetic system and the neural networks. A lower bound on population size is exhibited stating that the behaviour of the finite population system, in case of sufficiently large sizes, can be suitably
openaire +1 more source
The Bulletin of Mathematical Biophysics, 1948
The structure of a complete or incomplete neural net is represented here by several matrices. The activity equation of the net follows in a general form. A chain or cycle is defined as a neural structure whose connection matrix is unitary. We can compute the number of simple chains by a recurrent formula.
openaire +2 more sources
The structure of a complete or incomplete neural net is represented here by several matrices. The activity equation of the net follows in a general form. A chain or cycle is defined as a neural structure whose connection matrix is unitary. We can compute the number of simple chains by a recurrent formula.
openaire +2 more sources
1998
Abstract On first thought, modeling networks of neurons would seem to be an enterprise having little in common with modeling a checkersplayer. My own first reaction to Art Samuel’s checkersplayer, as I mentioned earlier, was to think the ideas fascinating but far removed from the study of neural networks.
James J. Buckley, Thomas Feuring
openaire +2 more sources
Abstract On first thought, modeling networks of neurons would seem to be an enterprise having little in common with modeling a checkersplayer. My own first reaction to Art Samuel’s checkersplayer, as I mentioned earlier, was to think the ideas fascinating but far removed from the study of neural networks.
James J. Buckley, Thomas Feuring
openaire +2 more sources
2001
Conventional neural networks work by changing the synaptical weights between their neurons. New neural nets (NNN) are presented, using the recording of temporal sequences of activity, generated by various patterns in chains of neurons, to store and reproduce those patterns.
openaire +1 more source
Conventional neural networks work by changing the synaptical weights between their neurons. New neural nets (NNN) are presented, using the recording of temporal sequences of activity, generated by various patterns in chains of neurons, to store and reproduce those patterns.
openaire +1 more source
Neural Nets: An Evaluation and a Spreadsheet Implementation
Creativity and Innovation Management, 1996Attitudes to neural nets range from suspicion to uncritical admiration. This paper aims to introduce nets and to evaluate their strengths and weaknesses. The language is non‐technical, but the conceptual treatment is intended to be rigorous. A practical method for implementing a neural net on a spreadsheet is described, and sample results illustrated.
openaire +1 more source
Survival analysis and neural nets
Statistics in Medicine, 1994AbstractWe consider feed‐forward neural nets and their relation to regression models for survival data. We show how the back‐propagation algorithm may be used to obtain maximum likelihood estimates in certain standard regression models for survival data, as well as in various generalizations of these.
Liestøl, K. +2 more
openaire +2 more sources
A stochastic architecture for neural nets
IEEE International Conference on Neural Networks, 1988A stochastic digital architecture is described for simulating the operation of Hopfield neural networks. This architecture provides reprogrammability (since synaptic weights are stored in digital shift registers), large dynamic range (by using either fixed or floating-point weights), annealing (by coupling variable neuron gains with noise from ...
David E. van den Bout +1 more
openaire +2 more sources
Methods of analysis of neural nets
Biological Cybernetics, 1976Two general methods of analysis of neural nets are developed in terms of elementary matrix algebra. These methods offer a complete description of the behaviors of neural nets with relative ease. As an example, the special case of two neurons is completely solved.
Caianiello, E. R., Grimson, W. E. L.
openaire +2 more sources