Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series : 28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, Part IV / / edited by Igor V. Tetko, Věra Kůrková, Pavel Karpov, Fabian Theis

• Pubblicazione: Cham : , : Springer International Publishing : , : Imprint : Springer, , 2019
• Edizione: 1st ed. 2019.
• Descrizione fisica: 1 online resource (XXX, 761 p. 339 illus., 198 illus. in color.)
• Disciplina: 006.3; 006.32
• Soggetto topico: Artificial intelligence; Computer vision; Computer engineering; Computer networks; Algorithms; Data protection; Artificial Intelligence; Computer Vision; Computer Engineering and Networks; Computer Communication Networks; Data and Information Security
• Persona (resp. second.): TetkoIgor V; KůrkováVěra; KarpovPavel; TheisFabian
• Nota di contenuto: An ensemble model for winning a Chinese machine reading comprehension competition -- Dependent Multilevel Interaction Network for Natural Language Inference -- Learning to Explain Chinese Slang Words -- Attention-Based Improved BLSTM-CNN for Relation Classification -- An Improved Method of Applying a Machine Translation Model to a Chinese Word Segmentation Task -- Interdependence Model for Multi-label Classification -- Combining deep learning and (structural) feature-based classification methods for copyright-protected PDF documents -- Collaborative Attention Network with Word and N-gram Sequences Modeling for Sentiment Classification -- Targeted Sentiment Classification with Attentional Encoder Network -- Capturing User and Product Information for Sentiment Classification via Hierarchical Separated Attention and Neural Collaborative Filtering -- Imbalanced Sentiment Classification Enhanced with Discourse Marker -- Revising Attention with Position for Aspect-level Sentiment Classification -- Surrounding-Based Attention Networks for Aspect-Level Sentiment Classification -- Mid Roll Advertisement Placement using Multi Modal Emotion Analysis -- DCAR: Deep Collaborative Autoencoder for Recommendation with Implicit Feedback -- Jointly Learning to Detect Emotions and Predict Facebook Reactions -- Discriminative Feature Learning for Speech Emotion Recognition -- A Judicial Sentencing Method Based on Fused Deep Neural Networks -- SECaps: A Sequence Enhanced Capsule Model for Charge Prediction -- Learning to Predict Charges for Judgment with Legal Graph -- A Recurrent Attention Network for Judgment Prediction -- Symmetrical Adversarial Training Nets: A Novel Model For Text Generation -- A Novel Image Captioning Method based on Generative Adversarial Networks -- Quality-Diversity Summarization with Unsupervised Autoencoders -- Conditional GANs for Image Captioning with Sentiments -- Neural Poetry: Learning to Generate Poems using Syllables -- Exploring the Advantages of Corpus in Neural Machine Translation of Agglutinative Language -- RL extraction of syntax-based chunks for sentence compression -- Robust Sound Event Classification with Local Time-Frequency Information and Convolutional Neural Networks -- Neuro-Spectral Audio Synthesis: Exploiting characteristics of the Discrete Fourier Transform in the real-time simulation of musical instruments using parallel Neural Networks -- Ensemble of Convolutional Neural Networks for P300 Speller in Brain Computer Interface -- Deep Recurrent Neural Networks with Nonlinear Masking Layers and Two-Level Estimation for Speech Separation -- Auto-Lag Networks for Real Valued Sequence to Sequence Prediction -- LSTM Prediction on Sudden Occurrence of Maintenance Operation of Air-conditioners in Real-time Pricing Adaptive Control -- Dynamic Ensemble Using Previous and Predicted Future Performance for Multi-Step-Ahead Solar Power Forecasting -- Timage – A Robust Time Series Classification Pipeline -- Prediction of the Next Sensor Event and its Time of Occurrence in Smart Homes -- Multi-task Learning Method for Hierarchical Time Series Forecasting -- Demand-prediction architecture for distribution businesses based on multiple RNNs with alternative weight update -- A Study of Deep Learning for Network Traffic Data Forecasting -- Composite Quantile Regression Long Short-Term Memory Network -- Short-Term Temperature Forecasting on a Several Hours Horizon -- Using Long Short-Term Memory for Wavefront Prediction in Adaptive Optics -- Incorporating Adaptive RNN-based Action Inference and Sensory Perception -- Quality of Prediction of Daily Relativistic Electrons Flux at Geostationary Orbit by Machine Learning Methods -- Soft Subspace Growing Neural Gas for DataStream Clustering -- Region Prediction from Hungarian Folk Music Using Convolutional Neural Networks -- Merging DBSCAN and Density Peak for Robust Clustering -- Market basket analysis using Boltzmann machines -- Dimensionality Reduction for Clustering and Cluster Tracking of Cytometry Data -- Improving Deep Image Clustering With Spatial Transformer Layers -- Collaborative Non-negative Matrix Factorization -- Cosine Similarity Drift Detector -- Unsupervised anomaly detection using optimal transport for predictive maintenance -- Robust Gait Authentication Using Autoencoder and Decision Tree -- MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks -- Intrusion Detection via Wide & Deep Model -- Towards Attention based Vulnerability Discovery using Source Code Representation -- Convolutional Recurrent Neural Networks for Computer Network Analysis.
• Sommario/riassunto: The proceedings set LNCS 11727, 11728, 11729, 11730, and 11731 constitute the proceedings of the 28th International Conference on Artificial Neural Networks, ICANN 2019, held in Munich, Germany, in September 2019. The total of 277 full papers and 43 short papers presented in these proceedings was carefully reviewed and selected from 494 submissions. They were organized in 5 volumes focusing on theoretical neural computation; deep learning; image processing; text and time series; and workshop and special sessions. .
• Titolo autorizzato: Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series
• ISBN: 3-030-30490-6
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910349299703321
• Lo trovi qui: Univ. Federico II
• Serie: Theoretical Computer Science and General Issues, . 2512-2029 ; ; 11730