[Paper Review] Flexible multitask computation in recurrent networks utilizes shared dynamical motifs

JaeHeon Lee, 이재헌·2024년 9월 16일
0

Paper Review

목록 보기
47/49
post-thumbnail

Flexible multitask computation in recurrent networks utilizes shared dynamical motifs

  • https://github.dev/lauradriscoll/flexible_multitask

  • set up 4 period (context, stimulus, memory, response)

    - input: 1(fixation) + 2(modalities) x 2(Asin(theta)andAcos(theta)) + 15(rule)
    - output: 1(fixation) + 1(modality) x 2(sin(phi) and cos(phi))
  • fixed point and stability of that fixed point via analyzing linearization matrix (jacobian)

  • single task network

    • shared fixed point in context dynamics, memory dynamics
    • during stimulus period, center → ring movement
    • during memory period, ring attractor shrink on memory PC subspace
      • by introducing interpolation alpha
  • two task networks (MemoryPro, MemoryAnti)

    • shared ring attractor & two separate stable FP, one unstable FP
      • by introducing ‘rule input’ interpolation alpha
  • task variance analysis - finding dynamical motifs
    - cluster 2 - reaction-timed response, cluster 9 - memory-guided responses
    - figure 3a. - cluster C has block → that color is for response
    - in fig 6, their ‘response’ dynamics interrupted with lesioned cluster c units

  • exploiting these dynamical motif (similar subspace) with “rule interpolation”
    - (PCA on memory state)
    - task period cluster 6, unit clusters t and u / 9,10 with a-d: shared point/ring attractor

  • shared stimulus period dynamical motifs

    • during stimulus period, if initial condition is similar, also is evolving steps.
    • during rule (context) period, network prepares future pathways (trajectories)
  • interpolation with rule inputs by alpha
    - (PCA on stimulus state)
    - “connection bridge” by alpha was orthogonal to decision boundary
    - similar task share stable and unstable fixed point

  • lesioning clustered RNN units - they found modular lesion effects on…

    • c: delayed response, f: anti-response task, modality 1/2, t/u: category memory, a/b continuous memory
  • reusing dynamical motifs

    • train all task except MemoryAnti, all freeze except the input weights
profile
https://jaeheon-lee486.github.io/

0개의 댓글