Filters








3,654 Hits in 3.5 sec

On Mining Conditions using Encoder-decoder Networks

Fernando Gallego, Rafael Corchuelo
2019 Proceedings of the 11th International Conference on Agents and Artificial Intelligence  
We propose a taxonomy classifier based on sequenceto-sequence neural networks, which are widely used in machine translation and automatic document summarization, by treating taxonomy classification as  ...  This paper describes our taxonomy classifier for SIGIR eCom Rakuten Data Challenge.  ...  Also, we would like to show our gratitude to Kento Nozawa and Taro Tezuka for comments that greatly improved the manuscript.  ... 
doi:10.5220/0007379506240630 dblp:conf/icaart/GallegoC19 fatcat:hkywltc6wbc7bocdqskt7typj4

Atlas: A Dataset and Benchmark for E-commerce Clothing Product Categorization [article]

Venkatesh Umaashankar, Girish Shanmugam S, Aditi Prakash
2019 arXiv   pre-print
Further, we establish the benchmark by comparing image classification and Attention based Sequence models for predicting the category path.  ...  Product categorization is a large scale classification task that assigns a category path to a particular product.  ...  Encoder and Decoder In Encoder, we use Convolutional Neural Network (CNN) to produce fixed size vectors.  ... 
arXiv:1908.08984v1 fatcat:n2hbzhbynnexjov7jxqxbnhhzq

Finding Reusable Machine Learning Components to Build Programming Language Processing Pipelines [article]

Patrick Flynn and Tristan Vanderbruggen and Chunhua Liao and Pei-Hung Lin and Murali Emani and Xipeng Shen
2022 arXiv   pre-print
However, it is challenging for new researchers and developers to find the right components to construct their own machine learning pipelines, given the diverse PLP tasks to be solved, the large number  ...  Chami et al. also present a taxonomy but with focus in graph representation learning (GRL) [6] . The taxonomy includes GRL from network embedding, graph regularization and graph neural networks.  ...  This categorization is common for a general purpose presentation of Neural Networks. We redirect the reader toward [15, 28] and [6] for taxonomies of NLP models and graph models, respectively.  ... 
arXiv:2208.05596v1 fatcat:4pp7zsxvynf35fraa2wz65epd4

Network Traffic Feature Engineering Based on Deep Learning

Kai Wang, Liyun Chen, Shuai Wang, Zengguang Wang
2018 Journal of Physics, Conference Series  
network encode.  ...  A network traffic feature extraction method based on autoencoder model is proposed.  ...  A multilevel taxonomy and requirements for an optimal traffic-classification model 2014 Int.  ... 
doi:10.1088/1742-6596/1069/1/012115 fatcat:nuwqqtiviraw7ea7pmgboiofrm

Efficient strategies for hierarchical text classification: External knowledge and auxiliary tasks [article]

Kervy Rivas Rojas, Gina Bustamante, Arturo Oncevay, Marco A. Sobrevilla Cabezudo
2020 arXiv   pre-print
Most of the studies have focused on developing novels neural network architectures to deal with the hierarchical structure, but we prefer to look for efficient ways to strengthen a baseline model.  ...  In hierarchical text classification, we perform a sequence of inference steps to predict the category of a document from top to bottom of a given class taxonomy.  ...  Finally, we acknowledge the support of NVIDIA Corporation with the donation of a Titan Xp GPU used for the study.  ... 
arXiv:2005.02473v2 fatcat:wowklmteubeavds2su6btmiokq

Machine Learning on Graphs: A Model and Comprehensive Taxonomy [article]

Ines Chami, Sami Abu-El-Haija, Bryan Perozzi, Christopher Ré, Kevin Murphy
2022 arXiv   pre-print
Specifically, we propose a Graph Encoder Decoder Model (GRAPHEDM), which generalizes popular algorithms for semi-supervised learning on graphs (e.g.  ...  The second, graph regularized neural networks, leverages graphs to augment neural network losses with a regularization objective for semi-supervised learning.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.  ... 
arXiv:2005.03675v3 fatcat:6eoicgprdvfbze732nsmpaumqe

Transformers in Time Series: A Survey [article]

Qingsong Wen, Tian Zhou, Chaoli Zhang, Weiqi Chen, Ziqing Ma, Junchi Yan, Liang Sun
2022 arXiv   pre-print
In this paper, we systematically review transformer schemes for time series modeling by highlighting their strengths as well as limitations through a new taxonomy to summarize existing time series transformers  ...  From the perspective of network modifications, we summarize the adaptations of module level and architecture level of the time series transformers.  ...  ., 2017] follows most competitive neural sequence models with an encoder-decoder structure. Both encoder and decoder are composed of multiple identical blocks.  ... 
arXiv:2202.07125v3 fatcat:q6vmkszqavbgrdtrbpsgaco7u4

Don't Classify, Translate: Multi-Level E-Commerce Product Categorization Via Machine Translation [article]

Maggie Yundi Li and Stanley Kok and Liling Tan
2018 arXiv   pre-print
Conventional methods for product categorization are typically based on machine learning classification algorithms.  ...  In our experiments on two large real-world datasets, we show that our approach achieves better predictive accuracy than a state-of-the-art classification system for product categorization.  ...  We thank RIT for the collaboration, support and computation resources for our experiments. We also thank Ali Cevahir for his advice on the CUDeep-related experiments.  ... 
arXiv:1812.05774v1 fatcat:ki545ztt4rcynhnzg4gyg3pwz4

A Comparative Study of Real-Time Semantic Segmentation for Autonomous Driving

Mennatullah Siam, Mostafa Gamal, Moemen Abdel-Razek, Senthil Yogamani, Martin Jagersand, Hong Zhang
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
The framework is scalable for addition of new encoders and decoders developed in the community for other vision tasks.  ...  We performed detailed experimental analysis on cityscapes dataset for various combinations of encoder and decoder.  ...  We implemented a generic framework through the decoupled encoder-decoder design. This allows the extensibility for more encoding and decoding methods.  ... 
doi:10.1109/cvprw.2018.00101 dblp:conf/cvpr/SiamGAYJ018 fatcat:4dq7v7fo55elppdw2iv3akwzou

An Attentive Survey of Attention Models [article]

Sneha Chaudhari, Varun Mithal, Gungor Polatkan, Rohan Ramanath
2021 arXiv   pre-print
Attention Model has now become an important concept in neural networks that has been researched within diverse application domains.  ...  We also describe how attention has been used to improve the interpretability of neural networks. Finally, we discuss some future research directions in attention.  ...  One could exploit this benefit to introduce hybrid encoder-decoders, the most popular being Convolutional Neural Network (CNN) as an encoder, and RNN or Long Short Term Memory (LSTM) as the decoder.  ... 
arXiv:1904.02874v3 fatcat:fyqgqn7sxzdy3efib3rrqexs74

Knowledge-aware Document Summarization: A Survey of Knowledge, Embedding Methods and Architectures [article]

Yutong Qu, Wei Emma Zhang, Jian Yang, Lingfei Wu, Jia Wu
2022 arXiv   pre-print
Particularly, we propose novel taxonomies to recapitulate knowledge and knowledge embeddings under the document summarization view.  ...  This paper pursues to present the first systematic survey for the state-of-the-art methodologies that embed knowledge into document summarizers.  ...  [25, 38] Encoder-Decoder based Approaches In this category, the encoder-decoder architecture is adopted for document summarization.  ... 
arXiv:2204.11190v2 fatcat:rx7x6l47xzaa3gubjfvyaexpem

A Variational Graph Autoencoder for Manipulation Action Recognition and Prediction [article]

Gamze Akyol, Sanem Sariel, Eren Erdal Aksoy
2021 arXiv   pre-print
Our network has a variational autoencoder structure with two branches: one for identifying the input graph type and one for predicting the future graphs.  ...  The current research trend heavily relies on advanced convolutional neural networks to process the structured Euclidean data, such as RGB camera images.  ...  Our proposed graph network has an encoder-decoder structure, where encoder involves multiple graph convolution [14] layers and decoder has two branches: one is for the action recognition task and the  ... 
arXiv:2110.13280v1 fatcat:6ywfdrextrc3bd32jjvsdhyqbm

Neural Attention Models in Deep Learning: Survey and Taxonomy [article]

Alana Santana, Esther Colombini
2021 arXiv   pre-print
For decades, concepts and functions of attention have been studied in philosophy, psychology, neuroscience, and computing. Currently, this property has been widely explored in deep neural networks.  ...  Here we propose a taxonomy that corroborates with theoretical aspects that predate Deep Learning.  ...  Firstly, the encoder/decoder RNNSearch [34], the decoder calculates from a context vector are recurrent neural networks, and the encoder  ... 
arXiv:2112.05909v1 fatcat:qk2gljrl2rdyfbxw62n5cu6hzu

Empirical Evaluation of the Effectiveness of Variational Autoencoders on Data Augmentation for the Image Classification Problem

Ozge Oztimur Karadag
2020 International Journal of Intelligent Systems and Applications in Engineering  
On the other hand, generative models such as generative adversarial networks, auto-encoders, after trained with a set of image learn to generate synthetic data.  ...  We evaluate the classification performance using various sized datasets and compare the classification performances on four datasets; dataset without augmentation, dataset augmented with VAE and two datasets  ...  Image Classification A Deep Convolutional Neural Network (CNN) architecture is used for classification of the images.  ... 
doi:10.18201/ijisae.2020261593 fatcat:lkhczvixwbeuvn6nc5dshaiyam

End-to-End Trainable Attentive Decoder for Hierarchical Entity Classification

Sanjeev Karn, Ulli Waltinger, Hinrich Schütze
2017 Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers  
We address fine-grained entity classification and propose a novel attention-based recurrent neural network (RNN) encoderdecoder that generates paths in the type hierarchy and can be trained end-to-end.  ...  We show that our model performs better on fine-grained entity classification than prior work that relies on flat or local classifiers that do not directly model hierarchical structure.  ...  We thank Stephan Baier, Siemens CT members and the anonymous reviewers for valuable feedback. This research was supported by Bundeswirtschaftsministerium (bmwi. de), grant 01MD15010A (Smart Data Web).  ... 
doi:10.18653/v1/e17-2119 dblp:conf/eacl/SchutzeWK17 fatcat:frulzitxgrdsvbaohokyxwtxf4
« Previous Showing results 1 — 15 out of 3,654 results