Functional approximation by perceptrons: a new approach
نویسندگان
چکیده
منابع مشابه
Multi-layer Perceptrons for Functional Data Analysis: A Projection Based Approach
In this paper, we propose a new way to use Functional MultiLayer Perceptrons (FMLP). In our previous work, we introduced a natural extension of Multi Layer Perceptrons (MLP) to functional inputs based on direct manipulation of input functions. We propose here to rely on a representation of input and weight functions thanks to projection on a truncated base. We show that the proposed model has t...
متن کاملStochastic Approximation and Multilayer Perceptrons: The Gain Backpropagation Algorithm
A standard general algorithm, the stochastic approximation algorithm of Albert and Gardner [1] , is applied in a new context to compute the weights of a multilayer per ceptron network. This leads to a new algorithm, the gain backpropagation algorithm, which is related to, but significantly different from, the standard backpropagat ion algorith m [2]. Some simulation examples show the potential ...
متن کاملTheoretical properties of functional Multi Layer Perceptrons
In this paper, we study a natural extension of Multi Layer Perceptrons (MLP) to functional inputs. We show that fundamental results for numerical MLP can be extended to functional MLP. We obtain universal approximation results that show the expressive power of functional MLP is comparable to the one of numerical MLP. We obtain consistency results which imply that optimal parameters estimation f...
متن کاملNew Analytical Approach for Reservoir Stress Approximation Based on Acid Fracturing Data
In this research attempts were made to estimate the in-situ stresses acting on a hydrocarbon reservoir based on routine activities of acid injection in oil reservoir. It was found that the relation between the re-opening pressure of fracture and principal in-situ stresses can be estimated using rock mechanics equations for the circular underground cavities. An appropriate relation between the m...
متن کاملMulti-layer perceptrons and probabilistic neural networks for phoneme recognition
Phoneme recognition can be viewed as classifying multivariate observations. Multi-layer perceptrons (MLP) and probabilistic neural networks (PNN) approach the decision problem using two complementary models. The MLP models the discriminant surfaces between different phoneme categories, essentially by piece-wise planar approximations, while the PNN approximates class conditional probability dens...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1995