Post #3195788

@GabrielBena@neuromatch.social Some of these come from Fodor, and later Shallice and Cooper: modules should have a sub-function, respond to only one type of input, impairing them shouldn't impair other modules, and have limited access to information outside their state. Can we quantify these? We came up with three quantified measures of functional modularity based on: (1) probing (can we infer information a module shouldn't have from its activity), (2) ablation (which sub-functions are impaired), (3) dependency on data that should be irrelevant (with correlation). We also designed a task and network designed to have maximal, controllable modularity. There are two modules (dense recurrent neural networks) with sparse interconnections. Each receives a separate input. Solving the task requires they share precisely one bit of information. Roughly speaking, the task is that each module is given one digit to observe. If the parity of the two digits is the same (both even or both odd) then return the first digit, otherwise the second digit. You can solve this by having each module only communicate one parity bit to the other.