Learn More
In this paper we consider a new paradigm of learning: learning using hidden information. The classical paradigm of the supervised learning is to learn a decision rule from labeled data (x<inf>i</inf>, y<inf>i</inf>), x<inf>i</inf> &#x2208; X, y<inf>i</inf> &#x2208; &#x007B;&#x2212;1, 1&#x007D;, i = 1, &#x2026;, &#x2113;. In this paper we consider a new(More)
  • 1