Tree-Based Convolutional Neural Networks : Principles and Applications /: Principles and Applications. (2018)

• Record Type: Book
• Further Information: Note: Lili Mou and Zhi Jin.
• Authors: Mou, Lili; Jin, Zhi, 1962-
• Contents: Intro; Preface; Acknowledgements; Contents; Acronyms; 1 Introduction; 1.1 Deep Learning Background; 1.2 Incorporating Structural Information into Neural Architectures; 1.3 The Proposed Tree-Based Convolutional Neural Networks; 1.4 Structure of the Book; References; 2 Background and Related Work; 2.1 Generic Neural Networks; 2.1.1 Neuron and Multilayer Network; 2.1.2 Training Objectives; 2.1.3 Learning Neural Parameters; 2.1.4 Pretraining Neural Networks; 2.2 Neural Networks for Natural Language Processing; 2.2.1 Specialty of Natural Language Processing; 2.2.2 Neural Language Models 2.2.3 Word Embeddings2.3 Structure-Sensitive Neural Networks; 2.3.1 Convolutional Neural Network; 2.3.2 Recurrent Neural Network; 2.3.3 Recursive Neural Network; 2.4 Summary; References; 3 General Framework of Tree-Based Convolutional Neural Networks (TBCNNs); 3.1 General Idea and Formula of TBCNN; 3.2 Applications of TBCNN; 3.3 Difficulties in Designing TBCNN; 4 TBCNN for Programs' Abstract Syntax Trees; 4.1 Introduction; 4.2 The Proposed Approach; 4.2.1 Overview; 4.2.2 Representation Learning for AST Nodes; 4.2.3 Coding Layer; 4.2.4 Tree-Based Convolutional Layer; 4.2.5 Dynamic Pooling 4.2.6 The ``Continuous Binary Tree'' Model4.3 Experiments; 4.3.1 Unsupervised Program Vector Representations; 4.3.2 Classifying Programs by Functionalities; 4.3.3 Detecting Bubble Sort; 4.3.4 Model Analysis; 4.4 Summary and Discussion; References; 5 TBCNN for Constituency Trees in Natural Language Processing; 5.1 Background of Sentence Modeling and Constituency Trees; 5.2 Proposed Model; 5.2.1 Constituency Trees as Input; 5.2.2 Recursively Representing Intermediate Nodes; 5.2.3 Constituency Tree-Based Convolutional Layer; 5.2.4 Dynamic Pooling Layer; 5.3 Experiments; 5.3.1 Sentiment Analysis 5.3.2 Question Classification5.4 Summary and Discussions; References; 6 TBCNN for Dependency Trees in Natural Language Processing; 6.1 Background of Dependency Trees; 6.2 Proposed Model; 6.2.1 Dependency Trees as Input; 6.2.2 Convolutional Layer; 6.2.3 Dynamic Pooling Layer; 6.2.4 Applying d-TBCNN to Sentence Matching; 6.3 Experiments; 6.3.1 Discriminative Sentence Modeling; 6.3.2 Sentence Matching; 6.3.3 Model Analysis; 6.3.4 Visualization; 6.4 Conclusion and Discussion; References; 7 Conclusion and Future Work; 7.1 Conclusion; 7.2 Future Work; References; Index
• Publisher Details: Singapore : Springer Nature Springer
• Publication Date: 2018
• Extent: 1 online resource
• Subjects: 006.32; Computer science; Neural networks (Computer science); Machine learning; Artificial intelligence -- Data processing; COMPUTERS / General; Computers -- Database Management -- Data Mining; Computers -- Intelligence (AI) & Semantics; Computers -- Software Development & Engineering -- General; Data mining; Artificial intelligence; Software Engineering; Artificial intelligence; Data mining; Engineering; Software engineering; Electronic books
• Languages: English
• ISBNs: 9789811318702; 9811318700
• Related ISBNs: 9789811318696
• Notes: Note: Online resource; title from PDF title page (EBSCO, viewed October 4, 2018).
• Access Rights: Legal Deposit; Only available on premises controlled by the deposit library and to one user at any one time; The Legal Deposit Libraries (Non-Print Works) Regulations (UK).
• Access Usage: Restricted: Printing from this resource is governed by The Legal Deposit Libraries (Non-Print Works) Regulations (UK) and UK copyright law currently in force.