flâneur

Naren Manikandan

0 followers · 227 views

on the atlas — 4

highlights — 4

  • These assumptions are true when training an agent to play ATARI video games and other problems that reinforcement learning is currently applied to. However, they are violated for a general AI acting in the real world: this environment is partially observable since not all relevant information is available to the sensors at all times and not ergodic because some mistakes are just impossible to recover from (such as driving off a cliff). What makes general reinforcement learning general is that we are not making these assumptions.
    What is AIXI?
  • Generally these mappings can be stochastic
    What is AIXI?
  • Neural networks have a reputation for being better at solving statistical or approximate problems than at performing calculations or working with symbolic data. In this paper, we show that they can be surprisingly good at more elaborated tasks in mathematics, such as symbolic integration and solving differential equations. We propose a syntax for representing mathematical problems, and methods for generating large datasets that can be used to train sequence-to-sequence models. We achieve results that outperform commercial Computer Algebra Systems such as Matlab or Mathematica.
    [1912.01412] Deep Learning for Symbolic Mathematics
  • Starting [at a young age] he’s read everything that he could find about business. The subject that interests him, he’s read newspapers, biographies, trade press. He went over to his grandfather who was a grocer and he read the progressive grocer magazine, and he read articles on how to stock a meat department... What he’s really done is he’s created this immense vertical filing cabinet in his brain of layers and layers and layers of files of information that he can draw back on now for more than 70 years worth of data.
    Curius / Onboarding