Now showing items 1-9 of 9

    • Comparing various concepts of function prediction. Part 1. 

      Podnieks, Karlis (Latvia State University, 1974)
      Prediction: f(m+1) is guessed from given f(0), ..., f(m). Program synthesis: a program computing f is guessed from given f(0), ..., f(m). The hypotheses are required to be correct for all sufficiently large m, or with some ...
    • Comparing various concepts of function prediction. Part 2. 

      Podnieks, Karlis (Latvia State University, 1975)
      Prediction: f(m+1) is guessed from given f(0), ..., f(m). Program synthesis: a program computing f is guessed from given f(0), ..., f(m). The hypotheses are required to be correct for all sufficiently large m, or with some ...
    • Comparing various types of limiting synthesis and prediction of functions 

      Podnieks, Karlis (Latvia State University, 1974)
    • Computational complexity of prediction strategies 

      Podnieks, Karlis (Latvia State University, 1977)
      The value f(m+1) is predicted from given f(1), ..., f(m). For every enumeration T(n, x) there is a strategy that predicts the n-th function of T making no more than log2(n) errors (Barzdins-Freivalds). It is proved in the ...
    • Inductive inference of recursive functions: complexity bounds 

      Freivalds, Rusins; Barzdins, Janis; Podnieks, Karlis (Springer Verlag, 1991)
      This survey includes principal results on complexity of inductive inference for recursively enumerable classes of total recursive functions. Inductive inference is a process to find an algorithm from sample computations. ...
    • On speeding up synthesis and prediction of functions 

      Barzdins, Janis; Kinber, Efim; Podnieks, Karlis (Latvia State University, 1974)
    • Prediction of the next value of a function 

      Podnieks, Karlis (1981)
      The following model of inductive inference is considered. Arbitrary set tau = {tau_1, tau_2, ..., tau_n} of n total functions N->N is fixed. A "black box" outputs the values f(0), f(1), ..., f(m), ... of some function f ...
    • Probabilistic program synthesis 

      Podnieks, Karlis (Latvia State University, 1977)
      The following model of inductive inference is considered. Arbitrary numbering tau = {tau_0, tau_1, tau_2, ... } of total functions N->N is fixed. A "black box" outputs the values f(0), f(1), ..., f(m), ... of some function ...
    • Towards a theory of inductive inference 

      Barzdins, Janis; Podnieks, Karlis (1973)