Sciweavers

298 search results - page 22 / 60
» Optimizing number of hidden neurons in neural networks
Sort
View
ISNN
2007
Springer
14 years 2 months ago
Neural Networks Training with Optimal Bounded Ellipsoid Algorithm
Abstract. Compared to normal learning algorithms, for example backpropagation, the optimal bounded ellipsoid (OBE) algorithm has some better properties, such as faster convergence,...
José de Jesús Rubio, Wen Yu
IJCNN
2000
IEEE
14 years 8 days ago
Two Sites of Synaptic Integration: Relevant for Learning?
Since the classical work of D. O. Hebb [1] it has been assumed that synaptic plasticity solely depends on the activity of the pre- and the postsynaptic cell. Synapses influence th...
Konrad P. Körding, Peter König
PDCAT
2004
Springer
14 years 1 months ago
An Enhanced Fuzzy Neural Network
In this paper, we propose a novel approach for evolving the architecture of a multi-layer neural network. Our method uses combined ART1 algorithm and Max-Min neural network to self...
Kwang-Baek Kim, Young Hoon Joo, Jae-Hyun Cho
IJON
2007
184views more  IJON 2007»
13 years 7 months ago
Convex incremental extreme learning machine
Unlike the conventional neural network theories and implementations, Huang et al. [Universal approximation using incremental constructive feedforward networks with random hidden n...
Guang-Bin Huang, Lei Chen
NIPS
1997
13 years 9 months ago
Minimax and Hamiltonian Dynamics of Excitatory-Inhibitory Networks
A Lyapunov function for excitatory-inhibitory networks is constructed. The construction assumes symmetric interactions within excitatory and inhibitory populations of neurons, and...
H. Sebastian Seung, Tom J. Richardson, J. C. Lagar...