AbstractWe consider the problem of Learning Neural Networks from samples. The sample size which is sufficient for obtaining the almost-optimal stochastic approximation of function classes is obtained. In the terms of the accuracy confidence function, we show that the least-squares estimator is almost-optimal for the problem. These results can be used to solve Smale's network problem
AbstractIn neural network theory the complexity of constructing networks to approximate input-output...
The ability of a neural network to learn from experience can be viewed as closely related to its app...
Abstract. We prove that neural networks with a single hidden layer are capable of providing an optim...
We study the computational complexity of (deterministic or randomized) algorithms based on point sam...
We study the computational complexity of (deterministic or randomized) algorithms based on point sam...
The problem of adjusting the weights (learning) in multilayer feedforward neural networks (NN) is kn...
Artificial (or biological) Neural Networks must be able to form by learning internal memory of the e...
Artificial (or biological) Neural Networks must be able to form by learning internal memory of the e...
Artificial (or biological) Neural Networks must be able to form by learning internal memory of the e...
Artificial (or biological) Neural Networks must be able to form by learning internal memory of the e...
In the modern IT industry, the basis for the nearest progress is artificial intelligence technologie...
In the modern IT industry, the basis for the nearest progress is artificial intelligence technologie...
Abstract—The problem of approximating functions by neural networks using incremental algorithms is s...
The ability of a neural network to learn from experience can be viewed as closely related to its app...
AbstractApproximation properties of the MLP (multilayer feedforward perceptron) model of neural netw...
AbstractIn neural network theory the complexity of constructing networks to approximate input-output...
The ability of a neural network to learn from experience can be viewed as closely related to its app...
Abstract. We prove that neural networks with a single hidden layer are capable of providing an optim...
We study the computational complexity of (deterministic or randomized) algorithms based on point sam...
We study the computational complexity of (deterministic or randomized) algorithms based on point sam...
The problem of adjusting the weights (learning) in multilayer feedforward neural networks (NN) is kn...
Artificial (or biological) Neural Networks must be able to form by learning internal memory of the e...
Artificial (or biological) Neural Networks must be able to form by learning internal memory of the e...
Artificial (or biological) Neural Networks must be able to form by learning internal memory of the e...
Artificial (or biological) Neural Networks must be able to form by learning internal memory of the e...
In the modern IT industry, the basis for the nearest progress is artificial intelligence technologie...
In the modern IT industry, the basis for the nearest progress is artificial intelligence technologie...
Abstract—The problem of approximating functions by neural networks using incremental algorithms is s...
The ability of a neural network to learn from experience can be viewed as closely related to its app...
AbstractApproximation properties of the MLP (multilayer feedforward perceptron) model of neural netw...
AbstractIn neural network theory the complexity of constructing networks to approximate input-output...
The ability of a neural network to learn from experience can be viewed as closely related to its app...
Abstract. We prove that neural networks with a single hidden layer are capable of providing an optim...
DOI
Add to ORKG