11–14 of 14 posts
https://github.com/tensorflow/adanet looks effectively modular to me, although I wouldn't consider it the epitome of the same. One needs to be able to merge, move, and remove modules too.
Since non-linear neal models can approximate any function, I think that it makes sense to treat models as functions that are embedded in conventional applications. There are good deep learning wrappers for functional languages like Haskell and Clojure. I recently enjoyed the talk on juji.io which treats models as functions, leading to an interesting architecture.
You break big tasks into smaller tasks, which are generally manageable by people with 4-year degrees. An AI expert may manage or guide the larger project, but the sub-tasks shouldn't normally require an AI expert.
Since non-linear neal models can approximate any function, I think that it makes sense to treat models as functions that are embedded in conventional applications. There are good deep learning wrappers for functional languages like Haskell and Clojure. I recently enjoyed the talk on juji.io which treats models as functions, leading to an interesting architecture.
Do you have a permalink to that talk? I tried to go to their site but couldn't get past the 'Empathy Bot'