question
active
question:is-deep-learning-at-a-similar-albeit-more-modest-transition-point-as-the-invention-of-the-microscopeIs deep learning at a similar, albeit more modest, transition point as the invention of the microscope?
Motivating analogy question framing the circuits agenda as a potential paradigm shift in interpretability
Source paper
extracted_from(2020) · Chris Olah · Nick Cammarata · Ludwig Schubert · Gabriel Goh +2
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Asserts that the time is ripe for formal models.
- The paper's overarching constructive goal, paralleling Langton's 'life as it could be'
- Frames the paper's epistemic status and intent; invokes the traditional Buddhist metaphor to situate the formal model
- The mystery that beautiful geometry often yields good structural behavior is acknowledged but not yet fully explained mathematically.
- Even the beautiful descriptions of wholeness by scientists like Mae-Wan Ho remain mechanistic in detail and have not solved the bifurcation.
- Learning hierarchical representations of non-decomposable functions; proposed as formal equivalent to ETI process.
- Claim that principles of neurobiology apply to other tissues and systems.