полная версия
We show how to use "complementary priors" to eliminate the explaining-away effects that make inference difficult in densely connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can...
![Бейсик в задачах и примерах [2-е изд.]](https://www.rulit.me/data/programs/images/bejsik-v-zadachah-i-primerah-2-e-izd_911207.jpg)