To be clear, I was floating the simulators thing mainly as one example of a second story/interpretation which fits the paper’s observations but would generalize quite differently. The broader point is that the space of stories/interpretations consistent with the paper’s observations is big, and the paper has very much not done the work to justify the one specific interpretation it presents, or to justify the many subtle implications about generalization which that interpretation implies. The paper hasn’t even done the prerequisite work to justify the anthropomorphic concepts on which that interpretation is built (as Bengio was indicating). The paper just gives an interpretation, an interpretation which would have lots of implications about generalization not directly implied by the data, but doesn’t do any of the work needed to rule out the rest of of interpretation-space (including the many interpretations which would generalize differently).
To be clear, I was floating the simulators thing mainly as one example of a second story/interpretation which fits the paper’s observations but would generalize quite differently. The broader point is that the space of stories/interpretations consistent with the paper’s observations is big, and the paper has very much not done the work to justify the one specific interpretation it presents, or to justify the many subtle implications about generalization which that interpretation implies. The paper hasn’t even done the prerequisite work to justify the anthropomorphic concepts on which that interpretation is built (as Bengio was indicating). The paper just gives an interpretation, an interpretation which would have lots of implications about generalization not directly implied by the data, but doesn’t do any of the work needed to rule out the rest of of interpretation-space (including the many interpretations which would generalize differently).