Optimal colored perceptrons

نویسندگان
چکیده

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Parallel strategy for optimal learning in perceptrons

Abstract. We developed a parallel strategy for learning optimally specific realizable rules by perceptrons, in an on-line learning scenario. Our result is a generalisation of the Caticha-Kinouchi (CK) algorithm developed for learning a perceptron with a synaptic vector drawn from a uniform distribution over the N -dimensional sphere, so called the typical case. Our method outperforms the CK alg...

متن کامل

Optimal regularization of linear and nonlinear perceptrons

We derive an analytical formula for the generalization error of linear adaptive classifiers trained with weight decay. Analytical and experimental results are then presented to analyze the optimal value of regularization parameters as a function of the training set size.

متن کامل

Optimal bounds for the colored Tverberg problem

We prove a “Tverberg type” multiple intersection theorem. It strengthens the prime case of the original Tverberg theorem from 1966, as well as the topological Tverberg theorem of Bárány et al. (1980), by adding color constraints. It also provides an improved bound for the (topological) colored Tverberg problem of Bárány & Larman (1992) that is tight in the prime case and asymptotically optimal ...

متن کامل

Optimal Properties of Analog Perceptrons with Excitatory Weights

The cerebellum is a brain structure which has been traditionally devoted to supervised learning. According to this theory, plasticity at the Parallel Fiber (PF) to Purkinje Cell (PC) synapses is guided by the Climbing fibers (CF), which encode an 'error signal'. Purkinje cells have thus been modeled as perceptrons, learning input/output binary associations. At maximal capacity, a perceptron wit...

متن کامل

A polynomial training algorithm for calculating perceptrons of optimal stability

Recomi (Repeated correlation matrix inversion) is a polynomially fast algorithm for searching optimally stable solutions of the perceptron learning problem. For random unbiased and biased patterns it is shown that the algorithm is able to find optimal solutions, if any exist, in at worst O(N) floating point operations. Even beyond the critical storage capacity αc the algorithm is able to find l...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Physical Review E

سال: 2001

ISSN: 1063-651X,1095-3787

DOI: 10.1103/physreve.64.011915