|Название: Tree-Based Convolutional Neural Networks: Principles and Applications
Автор: Lili Mou, Zhi Jin
Формат: pdf (true), mobi, epub
Размер: 10.1 MB
In recent years, neural networks have become one of the most popular models in various applications of artificial intelligence, including image recognition, speech processing, and natural language processing. The convolutional neural network and the recurrent neural network are among the most popular neural architectures. The former uses a sliding window to capture translation invariant features; it typically works with signals in a certain dimensional space (e.g., 1D speech or 2D image). The latter is suitable to process time-series data as it iteratively aggregates information.
This book proposes a novel neural architecture, tree-based convolutional neural networks (TBCNNs),for processing tree-structured data. TBCNNsare related to existing convolutional neural networks (CNNs) and recursive neural networks (RNNs), but they combine the merits of both: thanks to their short propagation path, they are as efficient in learning as CNNs; yet they are also as structure-sensitive as RNNs.
In this book, readers will also find a comprehensive literature review of related work, detailed descriptions of TBCNNs and their variants, and experiments applied to program analysis and natural language processing tasks. It is also an enjoyable read for all those with a general interest in deep learning.
Скачать Tree-Based Convolutional Neural Networks: Principles and Applications