Abstract | ||
---|---|---|
In this paper, we consider the learning problem of multilayer perceptrons (MLPs) formulated as the problem of minimizing a smooth error function. As well known, the learning problem of MLPs can be a difficult nonlinear nonconvex optimization problem. Typical difficulties can be the presence of extensive flat regions and steep sided valleys in the error surface, and the possible large number of tra... |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/TNNLS.2015.2475621 | IEEE Transactions on Neural Networks and Learning Systems |
Keywords | Field | DocType |
Minimization,Training,Indexes,Optimization,Linear programming,Convergence,Approximation algorithms | Approximation algorithm,Error function,Computer science,Empirical risk minimization,Multilayer perceptron,Linear programming,Artificial intelligence,Artificial neural network,Perceptron,Optimization problem,Machine learning | Journal |
Volume | Issue | ISSN |
27 | 11 | 2162-237X |
Citations | PageRank | References |
3 | 0.37 | 16 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
L Grippo | 1 | 273 | 24.32 |
Andrea Manno | 2 | 3 | 0.37 |
M. Sciandrone | 3 | 335 | 29.01 |