are hippocampal architecture and bespoke neuroscience models capable of the general purpose computations studied in machine learning?

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• We hypothesize that general computational machines with sufficient resources possess the necessary and sufficient means to implement consciousness, and that successful implementation can be established via analysis or testing.hypothesis0.783
  The central hypothesis of the paper
• Winner take-all architectures of decision-making are already commonplace in computational neuroscience, and the softmax function provides a smooth approximation.claim0.779
  Neural plausibility argument for softmax policy selection.
• Neural networks, trained with different objectives on different data and modalities, are converging to a shared statistical model of reality in their representation spaces.quote0.776
  The paper's central thesis statement, presented prominently after the abstract
• Olah et al. (2020) found that automatically trained computer vision models, regardless of architecture and training procedure, all arrive at similar functional structures organizing similar features into similar compositional hierarchies, closely resembling the primate visual cortex.finding0.776
  Empirical finding supporting the Universality Hypothesis; extended by the paper to consciousness
• Connectionist models of cognition and learning identify conditions where collective intelligence can arise bottom-up, using only distributed learning mechanisms without system-level or global feedback.claim0.771
  Central claim about the power of connectionism.
• General computational machines with sufficient resources possess the necessary and sufficient means to implement consciousnesshypothesis0.771
  CIMC's central testable hypothesis grounding the entire research program
• Short-term cortical memory neurons may suffice for transformer-like computation in cortex without hippocampal involvement for non-long-term-memory taskshypothesis0.769
  Speculative hypothesis about how cortical transformer instantiation avoids requiring hippocampus.
• Different neural network models trained on different objectives and modalities are converging to a shared statistical model of reality in their representation spaceshypothesis0.767
  The central hypothesis of the paper; the platonic representation hypothesis itself