【11月16日 更新分】機械学習に関する論文まとめ

11月16日に公開された論文


ニューラルネットワーク

BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
著者:Zachary Lipton, Xiujun Li, Jianfeng Gao, Lihong Li, Faisal Ahmed, Li Deng
Less-forgetful Learning for Domain Expansion in Deep Neural Networks
著者:Heechul Jung, Jeongwoo Ju, Minju Jung, Junmo Kim
Interpreting Deep Visual Representations via Network Dissection
著者:Bolei Zhou, David Bau, Aude Oliva, Antonio Torralba
Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
著者:Yoshiaki Bando, Masato Mimura, Katsutoshi Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara

自然言語処理

“Found in Translation”: Predicting Outcomes of Complex Organic Chemistry Reactions using Neural Sequence-to-Sequence Models
著者:Philippe Schwaller, Theophile Gaudin, David Lanyi, Costas Bekas, Teodoro Laino
Using Noisy Extractions to Discover Causal Knowledge
著者:Dhanya Sridhar, Jay Pujara, Lise Getoor
Unsupervised Morphological Expansion of Small Datasets for Improving Word Embeddings
著者:Syed Sarfaraz Akhtar, Arihant Gupta, Avijit Vajpayee, Arjit Srivastava, Manish Shrivastava
Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time
著者:Pankaj Gupta, Subburam Rajaram, Hinrich Schütze, Bernt Andrassy
Words are Malleable: Computing Semantic Shifts in Political and Media Discourse
著者:Hosein Azarbonyad, Mostafa Dehghani, Kaspar Beelen, Alexandra Arkut, Maarten Marx, Jaap Kamps
Natural Language Inference with External Knowledge
著者:Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Diana Inkpen, Si Wei

画像解析

3D Face Reconstruction from Light Field Images: A Model-free Approach
著者:Mingtao Feng, Syed Zulqarnain Gilani, Yaonan Wang, Ajmal Mian
HandSeg: A Dataset for Hand Segmentation from Depth Images
著者:Sri Raghu Malireddi, Franziska Mueller, Markus Oberweger, Abhishake Kumar Bojja, Vincent Lepetit, Christian Theobalt, Andrea Tagliasacchi
Defense against Universal Adversarial Perturbations
著者:Naveed Akhtar, Jian Liu, Ajmal Mian
Learning Deeply Supervised Visual Descriptors for Dense Monocular Reconstruction
著者:Chamara Saroj Weerasekera, Ravi Garg, Ian Reid
Brain Extraction from Normal and Pathological Images: A Joint PCA/Image-Reconstruction Approach
著者:Xu Han, Roland Kwitt, Stephen Aylward, Bjoern Menze, Alexander Asturias, Paul Vespa, John Van Horn, Marc Niethammer
Interpreting Deep Visual Representations via Network Dissection
著者:Bolei Zhou, David Bau, Aude Oliva, Antonio Torralba
Dual-Path Convolutional Image-Text Embedding
著者:Zhedong Zheng, Liang Zheng, Michael Garrett, Yi Yang, Yi-Dong Shen
Convolutional Neural Networks and Data Augmentation for Spectral-Spatial Classification of Hyperspectral Images
著者:Jacopo Acquarelli, Elena Marchiori, Lutgarde M. C. Buydens, Thanh Tran, Twan van Laarhoven
No Reference Stereoscopic Video Quality Assessment Using Joint Motion and Depth Statistics
著者:Appina Balasubramanyam, Jalli Akshith, Battula Shanmukh Srinivas, Channappayya S Sumohana
A Public Image Database for Benchmark of Plant Seedling Classification Algorithms
著者:Thomas Mosgaard Giselsson, Rasmus Nyholm Jørgensen, Peter Kryger Jensen, Mads Dyrmann, Henrik Skov Midtiby
XGAN: Unsupervised Image-to-Image Translation for many-to-many Mappings
著者:Amélie Royer, Konstantinos Bousmalis, Stephan Gouws, Fred Bertsch, Inbar Moressi, Forrester Cole, Kevin Murphy

音声解析

Sound Event Detection in Synthetic Audio: Analysis of the DCASE 2016 Task Results
著者:Grégoire Lafay, Emmanouil Benetos, Mathieu Lagrange
Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition
著者:Shankar Kumar, Michael Nirschl, Daniel Holtmann-Rice, Hank Liao, Ananda Theertha Suresh, Felix Yu
Z-Forcing: Training Stochastic Recurrent Networks
著者:Anirudh Goyal, Alessandro Sordoni, Marc-Alexandre Côté, Nan Rosemary Ke, Yoshua Bengio
Human and Machine Speaker Recognition Based on Short Trivial Events
著者:Miao Zhang, Xiaofei Kang, Yanqing Wang, Lantian Li, Zhiyuan Tang, Haisheng Dai, Dong Wang
Emotional End-to-End Neural Speech Synthesizer
著者:Younggun Lee, Azam Rabiee, Soo-Young Lee

強化学習

Markov Decision Processes with Continuous Side Information
著者:Aditya Modi, Nan Jiang, Satinder Singh, Ambuj Tewari
Variational Adaptive-Newton Method for Explorative Learning
著者:Mohammad Emtiyaz Khan, Wu Lin, Voot Tangkaratt, Zuozhu Liu, Didrik Nielsen
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
著者:Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, Andrew McCallum
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
著者:Zachary Lipton, Xiujun Li, Jianfeng Gao, Lihong Li, Faisal Ahmed, Li Deng
AINOW
人工知能専門メディアAINOW(エーアイナウ)です。人工知能を知り・学び・役立てることができる国内最大級の人工知能専門メディアです。2016年7月に創設されました。取材のご依頼もどうぞ。https://form.run/@ainow-interview

無料メールマガジン登録

週1回、注目のAIニュースやイベント情報を
編集部がピックアップしてお届けしています。

こちらの規約にご同意のうえチェックしてください。

規約に同意する