Searching for authors named "Kalvis Apsitis" – sorted by Relevance.
6 documents found, showing 1 through 6.
-
Team Learning and Quasi-Closedness in Inductive Inference
- …. This paper investigates relations between team learning and a quasi-closedness property inherent in many identification types considered in inductive inference. This property is as follows: there exists such n that, if every union of n \Gamma 1 classes out of U1 ; : : : ; Un is identifiable, so…
- Add To MetaCart
-
Choosing a Learning Team: a Topological Approach
- …this paper we address the issue of how to compose teams. While this endeavor may sound like it belongs in the realm of psychology, it turns out that there are some interesting things that can be formally proved us- This work was facilitated by an international agreement under NSF Grant 9119540.…
- Cited by 3 (1 self) – Add To MetaCart
-
On Duality in Learning and the Selection of Learning Teams
- …Previous work in inductive inference dealt mostly with finding one or several machines (IIMs) that successfully learn a collection of functions. Herein we start with a class of functions and consider the learner set of all IIMs that are successful at learning the given class. Applying this perspe…
- Cited by 3 (2 self) – Add To MetaCart
-
On the Inductive Inference of Real Valued Functions
- …Introduction The starting point for studies in inductive inference is the model of learning by example introduced by Gold [Gol67]. This is a simple model of learning algorithms that input examples of some function and produce programs that are intended to compute the function generating the example…
- Cited by 1 (1 self) – Add To MetaCart
-
Inductive Inference of Real Functions
- …This paper investigates a model of inductive inference of realvalued functions from given argument-value pairs (x; h(x)), where h is the target function to be inferred. Both argument and value typically involve measurement errors, hence they are represented as pairs of rational numbers, i.e. an …
- Add To MetaCart
-
Hierarchies of Probabilistic and Team FIN-Learning
- …A FIN-learning machine M receives successive values of the function f it is learning and at some moment outputs a conjecture which should be a correct index of f . FIN learning has 2 extensions: (1) If M flips fair coins and learns a function with certain probability p, we have FINhpi-learning.…
- Cited by 4 (2 self) – Add To MetaCart
Showing 1 through 6.
