Аннотация
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 learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. The fast, greedy algorithm is used to initialize a slower learning procedure that fine-tunes the weights using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of handwritten digit images and their labels. This generative model gives better digit classification than the best discriminative learning algorithms. The low-dimensional manifolds on which the digits lie are modeled by long ravines in the free-energy landscape of the top-level associative memory, and it is easy to explore these ravines by using the directed connections to display what the associative memory has in mind.
![Kotlin в действии [Kotlin in Action]](https://www.rulit.me/data/programs/images/kotlin-v-dejstvii-kotlin-in-action_501842.jpg "Язык Kotlin предлагает выразительный синтаксис, мощную и понятную систему типов, великолепную поддержку и бесшовную совместимость с существующим кодом на Java,...")
![Чистый Python [Тонкости программирования для профи]](https://www.rulit.me/data/programs/images/chistyj-python-tonkosti-programmirovaniya-dlya-profi_554913.jpg "Изучение всех возможностей Python — сложная задача, а с этой книгой вы сможете сосредоточиться на практических навыках, которые действительно важны. Раскопайте...")
Комментарии к книге "A Fast Learning Algorithm for Deep Belief Nets"