Machine Learning – Should Decision Based Systems Generate Readable Thought Strings?

My idea is simple.

I think it would be better if decision based machine learning systems generate their own “thought” strings. That is. Text strings that are reflective of the instructions to itself. I think this is better than to rely on low level weight information. Even though its all supervised learning.

I mean error checking would be much easier than to retrain the whole system.

(Visited 18 times, 1 visits today)