Carlos E. Perez
Sep 4, 2018 · 1 min read

This is indeed a very good point. Predicting behavior of complex system (i.e. those exhibiting universality) is predictable up to a certain point (i.e. 8 Lyapunov times). This doesn’t violate the Church-Turing thesis. Pragmatically, we don’t need to show that a Turing machine halts, we only need to predict behavior as far as needed. This is in fact the function of cognition found in life forms. Predict the near future and not necessarily the far future.

    Carlos E. Perez

    Written by

    Author of Artificial Intuition and the Deep Learning Playbook — http://linkedin.com/in/ceperez https://twitter.com/IntuitMachine