Collection of papers and articles that I’ve spotted since my previous links post that seem interesting.




  • Neuroscience-inspired artificial intelligence
  • The limitations of deep learning
    • Say, for instance, that you could assemble a dataset of hundreds of thousands—even millions—of English language descriptions of the features of a software product, as written by a product manager, as well as the corresponding source code developed by a team of engineers to meet these requirements. Even with this data, you could not train a deep learning model to simply read a product description and generate the appropriate codebase. That's just one example among many. In general, anything that requires reasoning—like programming, or applying the scientific method—long-term planning, and algorithmic-like data manipulation, is out of reach for deep learning models, no matter how much data you throw at them. Even learning a sorting algorithm with a deep neural network is tremendously difficult.
    • This is because a deep learning model is "just" a chain of simple, continuous geometric transformations mapping one vector space into another.
  • Deep neural networks do not recognize negative images
  • Machine creativity beats some modern art
    • Objective evidence of sorts for the superiority of classical art, imho. Harder to replicate with machines due to greater complexity.




Comments from WordPress

  • Linv Linv 2017-07-23T05:25:56Z

    Why is Nagel-Sunstein-Holmes-Murray bad?

  • Linv Linv 2017-07-23T05:26:33Z


  • Rational Feed – deluks917 2017-07-22T22:29:29Z

    […] Links 10 by Artir (Nintil) – Tons of links. Economics, Psychology, AI, Philosophy, Misc. […]