𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Time-delay neural networks, volterra series, and rates of approximation

✍ Scribed by Irwin W. Sandberg

Publisher
Springer
Year
1998
Tongue
English
Weight
649 KB
Volume
17
Category
Article
ISSN
0278-081X

No coin nor oath required. For personal study only.

πŸ“œ SIMILAR VOLUMES

Neural networks and volterra series for
Neural networks and volterra series for time-domain power amplifier behavioral models
✍ F. Giannini; P. Colantonio; G. Orengo; A. Serino; G. Stegmayer; M. Pirola; G. Gh πŸ“‚ Article πŸ“… 2007 πŸ› John Wiley and Sons 🌐 English βš– 450 KB

This paper presents a black-box model that can be applied to characterize the nonlinear dynamic behavior of power amplifiers (PAs), including strong nonlinearities and memory effects. Feedforward time-delay Neural Networks (TDNN) are used to extract the model from a large-signal input-output time-do

Representations and rates of approximati
Representations and rates of approximation of real-valued Boolean functions by neural networks
✍ V. KΕ―rkovΓ‘; P. SavickΓ½; K. HlavÑčkovΓ‘ πŸ“‚ Article πŸ“… 1998 πŸ› Elsevier Science 🌐 English βš– 138 KB

We give upper bounds on rates of approximation of real-valued functions of d Boolean variables by one-hidden-layer perceptron networks. Our bounds are of the form c/ n p where c depends on certain norms of the function being approximated and n is the number of hidden units. We describe sets of funct