Tree-based convolutional neural networks principles and applications /

This book proposes a novel neural architecture, tree-based convolutional neural networks (TBCNNs), for processing tree-structured data. TBCNNs are related to existing convolutional neural networks (CNNs) and recursive neural networks (RNNs), but they combine the merits of both: thanks to their short...

Full description

Main Author: Mou, Lili,
Other Authors: Jin, Zhi,, SpringerLink (Online service)
Format: eBook
Language: English
Published: Singapore : Springer, [2018]
Physical Description: 1 online resource.
Series: SpringerBriefs in computer science.
Subjects:
Summary: This book proposes a novel neural architecture, tree-based convolutional neural networks (TBCNNs), for processing tree-structured data. TBCNNs are 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.
Item Description: Includes bibliographical references and index.
Introduction -- Preliminaries and Related Work -- General Concepts of Tree-Based Convolutional Neural Networks (TBCNNs) -- TBCNN for Programs' Abstract Syntax Trees (ASTs) -- TBCNN for Constituency Trees in Natural Language Processing -- TBCNN for Dependency Trees in Natural Language Processing -- Concluding Remarks.
This book proposes a novel neural architecture, tree-based convolutional neural networks (TBCNNs), for processing tree-structured data. TBCNNs are 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.
Physical Description: 1 online resource.
Bibliography: Includes bibliographical references and index.
ISBN: 9789811318702
9811318700