Transformations that Preserve Learnability

نویسندگان

  • Andris Ambainis
  • Rusins Freivalds
چکیده

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

On certain semigroups of transformations that preserve double direction equivalence

Let TX be the full transformation semigroups on the set X. For an equivalence E on X, let TE(X) = {α ∈ TX : ∀(x, y) ∈ E ⇔ (xα, yα) ∈ E}It is known that TE(X) is a subsemigroup of TX. In this paper, we discussthe Green's *-relations, certain *-ideal and certain Rees quotient semigroup for TE(X).

متن کامل

On conformal transformation of special curvature of Kropina metrics

      An important class of Finsler metric is named Kropina metrics which is defined by Riemannian metric α and 1-form β  which have many applications in physic, magnetic field and dynamic systems. In this paper, conformal transformations of χ-curvature and H-curvature of Kropina metrics are studied and the conditions that preserve this quantities are investigated. Also it is shown that in the ...

متن کامل

On descent for coalgebras and type transformations

We find a criterion for a morphism of coalgebras over a Barr-exact category to be effective descent and determine (effective) descent morphisms for coalgebras over toposes in some cases. Also, we study some exactness properties of endofunctors of arbitrary categories in connection with natural transformations between them as well as those of functors that these transformations induce between co...

متن کامل

Robust commitments and partial reputation

How should agents shape a finite “reputational" history to their advantage knowing that others will be learning from that history? We focus on one leader interacting with multiple followers and show that in most non-zero-sum games, the traditional Stackelberg mixed commitment is very fragile to observational uncertainty. We propose robust commitment rules that anticipate being learned and show ...

متن کامل

Tailoring Representations to Different Requirements

Designing the representation languages for the input and output of a learning algorithm is the hardest task within machine learning applications. Transforming the given representation of observations into a well-suited language LE may ease learning such that a simple and eecient learning algorithm can solve the learning problem. Learnability is deened with respect to the representation of the o...

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

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1996