Search

Now showing items 1-2 of 2

    • Can neural networks holistically reprogram themselves through their own observation? 

      Mariage, Jean-Jacques (BrSTU, 2006)
      Neural networks (NNs) are inspired -at least metaphorically -from biological solutions nature selected by evolution. On one hand, learning algorithms' efficacy has been widely demonstrated experimentally, even if the mathematical proof of their convergence is not always very easy to establish (SOM). ...

      2023-11-23

    • Learning From The Environment With A Universal Reinforcement Function 

      Bendersky, Diego; Santos, Juan Miguel (2006)
      Traditionally, in Reinforcement Learning, the specification of the task Ls contained in the reinforcement function (RF), and ach new task requires the definition of a new RF. But in the nature, explicit reward signals are limited, and the characteristics of the environment afTects not only how animals ...

      2023-11-23