DictionaryForumContacts

   Russian
Terms for subject Artificial intelligence containing слой | all forms | exact matches only
RussianEnglish
нейронный слойneural layer (в искусственной нейронной сети; из кн.: Дорогов А.Ю. Теория и проектирование быстрых перестраиваемых преобразований и слабосвязанных нейронных сетей Alex_Odeychuk)
свёрточный слойconvolutional layer (искусственной нейронной сети | A convolutional layer contains a set of filters whose parameters need to be learned. The height and weight of the filters are smaller than those of the input volume. Each filter is convolved with the input volume to compute an activation map made of neurons. In other words, the filter is slid across the width and height of the input and the dot products between the input and filter are computed at every spatial position. The output volume of the convolutional layer is obtained by stacking the activation maps of all filters along the depth dimension. Since the width and height of each filter is designed to be smaller than the input, each neuron in the activation map is only connected to a small local region of the input volume. In other words, the receptive field size of each neuron is small, and is equal to the filter size. The local connectivity is motivated by the architecture of the animal visual cortex where the receptive fields of the cells are small. The local connectivity of the convolutional layer allows the network to learn filters which maximally respond to a local region of the input, thus exploiting the spatial local correlation of the input (for an input image, a pixel is more correlated to the nearby pixels than to the distant pixels). In addition, as the activation map is obtained by performing convolution between the filter and the input, the filter parameters are shared for all local positions. The weight sharing reduces the number of parameters for efficiency of expression, efficiency of learning, and good generalization. Alex_Odeychuk)
слой подвыборкиsubsampling layer (Alex_Odeychuk)
слой подгонки, адаптирующий слойadaptation layer (Слой в составе нейросети, предназначенный для подгонки размера вектора данных к размерности входа нейросети Valeriy_Yatsenkov)
слой представления знанийlayer of representation (контекстуальный перевод на русс. язык Alex_Odeychuk)
сокращение избыточных нейронов в скрытых слояхpruning (искусственной нейронной сети Alex_Odeychuk)
субдискретизирующих слойsubsampling layer (Alex_Odeychuk)
эталонный слойpattern layer (один из невидимых слоев (hidden layer) в обобщенно-регрессионной нейронной сети (GRNN) MrBonD)