𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Geometry of learning: Visualizing the performance of neural network supervised training methods

✍ Scribed by G.S. Androulakis; G.D. Magoulas; M.N. Vrahatis

Publisher
Elsevier Science
Year
1997
Tongue
English
Weight
446 KB
Volume
30
Category
Article
ISSN
0362-546X

No coin nor oath required. For personal study only.

πŸ“œ SIMILAR VOLUMES

Performance comparison between the train
Performance comparison between the training method and the numerical method of the orthogonal neural network in function approximation
✍ Chen-San Chen; Ching-Shiow Tseng πŸ“‚ Article πŸ“… 2004 πŸ› John Wiley and Sons 🌐 English βš– 355 KB

The orthogonal neural network is a recently developed neural network based on the properties of orthogonal functions. It can avoid the drawbacks of traditional feedforward neural networks such as initial values of weights, number of processing elements, and slow convergence speed. Nevertheless, it n

Evaluation of nonlinear optimization met
Evaluation of nonlinear optimization methods for the learning algorithm of artificial neural networks
✍ Hideyuki Takagi; Shigeo Sakaue; Hayato Togawa πŸ“‚ Article πŸ“… 1992 πŸ› John Wiley and Sons 🌐 English βš– 980 KB

## Abstract This paper describes the implementation of nonlinear optimization methods into the learning of neural networks (NN) and the speed efficiency of four proposed improvements into the backpropagation algorithm. The problems of the backpropagation learning method are pointed out first, and t