flâneur

Neural wiring diagrams for message passing in multiscale organizations – Topos Institute

topos.site · 2,851 words · saved by 1 readers

In our recent paper, “Dynamic task delegation for hierarchical agents”, Sophie Libkind and I described a task delegation from an agent to a team of subordinates as morphisms in a certain operad called 𝑂 𝑟 𝑔 𝑚 Org m ​ . However, such morphisms include a great deal of data, and the examples we gave there barely scratched the surface of what’s possible. In this post I’ll show how “recumbent” neural wiring diagrams—with arbitrary feedback and “axon” splitting—give rise to a message-passing language for describing certain such task delegations. That is, I’ll define a cyclic operad 𝑟 𝑛 𝑊 𝐷 rnWD and a functor 𝑟 𝑛 𝑊 𝐷 → 𝑂 𝑟 𝑔 𝑚 rnWD→Org m ​ . In our recent paper, “Dynamic task delegation for hierarchical agents”, Sophie Libkind and I described what we called task delegations, procedures involving an agent and a team of subordinates, as the morphisms in a certain operad 𝑂 𝑟 𝑔 𝑚 Org m ​ . Think of agents as things that perform tasks, like travel agents, agent 007, a

Neural wiring diagrams for message passing in multiscale organizations – Topos Institute Warning Edit The arXiv paper that this post cites contains an error, and had to be taken down for the time being. However, the math in this post still stands. 1 1 Introduction In our recent paper, “Dynamic task delegation for hierarchical agents” , 2 Sophie Libkind and I described what we called task delegations , procedures involving an agent and a team of subordinates, as the morphisms in a certain operad \mathbb{O}\mathbf{rg}_\mathfrak{m} . Think of agents as things that perform tasks, like travel agent

saved by

related reading