Human gaming tactics draw analogies from the physical world to hide the underlying complexity (chunking), and enable the players to think at a higher level. AlphaGo isnt limited(?) by physical world analogies.
The limitations of backpropagation learning can now be overcome by using multilayer neural networks that contain top-down connections and training them to /generate/ sensory data rather than to classify it. (...) much better than previous approaches
„Viele mieten Links an, um deren Ranking in Suchmaschinen zu verbessern. Lassen Sie sich die Links Ihrer Mitbewerber anzeigen. So erfahren Sie warum diese in der Suchmaschine vor Ihnen stehen oder (hoffentlich) hinter Ihnen.“