Training of feedforward networks can be viewed as an unconstrained optimization problem. BP is slow to converge when the error surface is flat along a weight dimension. Second-order optimization techniques have a strong theoretical basis and provide significantly...
CITATION STYLE
Du, K.-L., & Swamy, M. N. S. (2014). Multilayer Perceptrons: Other Learning Techniques. In Neural Networks and Statistical Learning (pp. 127–157). Springer London. https://doi.org/10.1007/978-1-4471-5571-3_5
Mendeley helps you to discover research relevant for your work.