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.
![Using Asyncio in Python [Understanding Python’s Asynchronous Programming Features]](https://www.rulit.me/data/programs/images/using-asyncio-in-python-understanding-python-s-asynchronous_606937.jpg "Python 3.4 introduced the asyncio library, and Python 3.5 produced the async and await keywords to use it palatably. These new additions allow so-called asynchronousprogramming.
All of these new features, which I’ll refer to under the single name Asyncio, have been received by the Python...")
![Прикладной анализ текстовых данных на Python [Машинное обучение и создание приложений обработки естественного языка]](https://www.rulit.me/data/programs/images/prikladnoj-analiz-tekstovyh-dannyh-na-python-mashinnoe-obuchenie-i-soz_603555.jpg "Технологии анализа текстовой информации стремительно меняются под влиянием машинного
обучения. Нейронные сети из теоретических научных исследований перешли в...")
Комментарии к книге "A Fast Learning Algorithm for Deep Belief Nets"