Kalvis Apsitis

Learn More
Kalvis Apsitis Rtisig5 Freivaldst Carl H. Smith$ Institute of Mathematics Institute of Mathematics Department of Computer Science and Computer Science and Computer Science University of Maryland University of Latvia University of Latvia College Park, MD 20742 USA Raiqa bulviiris 29 Raiqa bulviiris 29 smith@cs. umd. edu LV-1459, Riga, Latvia LV-1459, Rigs,(More)
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 ips fair coins and learns a function with certain probability p, we have FIN hpi-learning. (2) When n machines simultaneously try to learn the same function(More)
J.Barzdin [Bar74] has proved that there are classes of total recursive {unctions which are FX-identifiable but their union is not. We prove that there are no 3 classes U I, U~, U s such that U~uU 2, UIuU 3, and U2uU s would be in EX but UIMU2uU3~ EX. For FINidentification there are 3 classes with the above-mentioned properly and there are no 4 classes Uj, U(More)
We generalize the traditional concept of team learning. The success of an asymmetric team in learning some function depends upon the successes of participant machines by an arbitrary nondecreasing Boolean function. Asymmetric team types are ordered accordingly to their learning power by basic reductions. The problem to determine this order for an arbitrary(More)
In this paper we investigate in which cases unions of identi$able classes are also necessarily identi$able. We consider identi$cation in the limit with bounds on mindchanges and anomalies. Though not closed under the set union, these identi$cation types still have features resembling closedness. For each of them we $nd n such that (1) if every union of n −(More)
We combine traditional studies of inductive inference and classical continuous mathematics to produce a study of learning real-valued functions. We consider two possible ways to model the learning by example of functions with domain and range the real numbers. The first approach considers functions as represented by computable analytic functions. The second(More)