Agent-environment approach to the simulation of Turing machines by neural networks

We propose a way to simulate Turing machines (TMs) by neural networks (NNs) which is in agreement with the correct interpretation of Turing's analysis of computation; compatible with the current approaches to analyze cognition as an interactive agent-environment process; and physically realizable since it does not use connection weights with unbounded precision. We give a full description of an implementation of a universal TM into a recurrent sigmoid NN focusing on the TM finite state control, leaving the tape, an infinite resource, as an external non-intrinsic feature.