In this paper, a model of analogy-based learning is presented, whose main novelty is the crucial ability to produce analogies in multi-dimensional input and output spaces. Evaluations are performed on various word pronunciation tasks, revealing the effectiveness of such joint learning strategies.

In a range of contexts, one comes across processes resembling inference, but where input propositions are not in general included among outputs, and the operation is not in any way reversible. Examples arise in contexts of conditional obligations, goals, ideals, preferences, actions, and beliefs. Our purpose is to develop a general theory of propositional input/output operations. Particular att...

In this work, the object of study is economy region. To describe it, a regular method for constructing difference input - output dynamic models proposed. This approach involves modeling not only sphere production, but also consumption. do this, vector phase variables includes gross domestic product. The variability model consists in ability to take into account various macroeconomic parameters ...

This paper proposes an input/output interpretation of supervision of discrete event systems. New concepts must be introduced in order to describe the behavior of the closed-loop system of plant and supervisor subject to communication delays. This paper further characterizes the class of supervisors allowed under delays for the general case and for additional assumptions on the plant language.