All

What are you looking for?

All
Projects
Results
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

Filters

45 607 (0,134s)

Result

Minimization of Empirical Error over Perceptron Networks

Supervised learning by perceptron networks is investigated as an approximate minimization of empirical error functional.

BA - Obecná matematika

  • 2005
  • D
Result

Learning from Data as an Optimization and Inverse Problem

Learning form data is investigated as minimization of empirical error functional in spaces of continuous functions and spaces defined by kernels. Using methods from theory of inverse problems, an alternative proof of Repres...

IN - Informatika

  • 2012
  • D
  • Link
Result

Learning from Data as an Inverse Problem

We reformulate the problem of minimization of an empirical error functional as a linear inverse problem by introducing an operator defined in terms of evaluations at the input data....

BA - Obecná matematika

  • 2004
  • D
Result

Learning with Generalization Capability by Kernel Methods of Bounded Complexity

Learning from data with generalization capability is studied in the framework of minimization of regularized empirical error functionals over nested families of hypothesis sets with increasing model complexity....

BA - Obecná matematika

  • 2005
  • Jx
Result

Learning from Data by Neural Networks of Limited Complexity.

Learning from data formalized as a minimization of a relularized empirical error is studied in terms of approximate minimization over sets of functions computable by networks with increasing number of hidden units....

BA - Obecná matematika

  • 2003
  • D
Result

Neural Networks Learning as Approximate Optimization.

Learning from data will be studied in the framework of approximate minimization of regularized empirical error functionals. There will be derived estimates of speed of convergence of infima achievable over approximations of...

BA - Obecná matematika

  • 2003
  • D
Result

Approximate Minimization of the Regularized Expected Error over Kernel Models

Learning from data under constraints on model complexity is studied in terms of rates of approximate minimization of the regularized expected error functional defining the expected error. As a special case, estimates of rat...

BA - Obecná matematika

  • 2008
  • Jx
Result

High-field side error field effects on H-mode plasma performance and their correction in ITER-like experiments on COMPASS

corresponds to the minimization of the coupling of the error field to the core plasma.The effect of high field side error fields on H-mode plasmas of different beta as obesrved experimentally is presented. Furthermore the ...

Fluids and plasma physics (including surface physics)

  • 2018
  • D
Result

Inverse Problems in Learning from Data

It is shown that application of methods from theory of inverse problems to learning from data leads to simple proofs of characterization of minima of empirical and expected error functionals and their regularized versions. The refor...

IN - Informatika

  • 2010
  • D
Result

Existence and Uniqueness of Minimization Problems with Fourier Based Stabilizers

We study minimization of regularized empirical error functional with a Fourier-based stabilizer. We prove existence and uniqueness of the solution. We also describe the shape of the minimizing function and show tha...

BA - Obecná matematika

  • 2004
  • D
  • 1 - 10 out of 45 607