[1807.04800] Feature Selection for Gender Classification in TUIK Life Satisfaction Survey
https://arxiv.org/abs/1807.04800
As known, attribute selection is a method that is used before the classification of data mining. In this study, a new data set has been created by using attributes expressing overall satisfaction in Turkey Statistical Institute (TSI) Life Satisfaction Survey dataset. Attributes are sorted by Ranking search method using attribute selection algorithms in a data mining application. These selected attributes were subjected to a classification test with Naive Bayes and Random Forest from machine learning algorithms. The feature selection algorithms are compared according to the number of attributes selected and the classification accuracy rates achievable with them. In this study, which is aimed at reducing the dataset volume, the best classification result comes up with 3 attributes selected by the Chi2 algorithm. The best classification rate was 73% with the Random Forest classification algorithm.
[1807.04798] Hydranet: Data Augmentation for Regression Neural Networks
https://arxiv.org/abs/1807.04798
Despite recent efforts, deep learning techniques remain often heavily dependent on a large quantity of labeled data. This problem is even more challenging in medical image analysis where the annotator expertise is often scarce. In this paper we propose a novel data-augmentation method to regularize neural network regressors, learning from a single global label per image. The principle of the method is to create new samples by recombining existing ones. We demonstrate the performance of our algorithm on two tasks: the regression of number of enlarged perivascular spaces in the basal ganglia; and the regression of white matter hyperintensities volume. We show that the proposed method improves the performance even when more basic data augmentation is used. Furthermore we reached an intraclass correlation coefficient between ground truth and network predictions of 0.73 on the first task and 0.86 on the second task, only using between 25 and 30 scans with a single global label per scan for training. To achieve a similar correlation on the first task, state-of-the-art methods needed more than 1000 training scans.
[1807.05076] Metalearning with Hebbian Fast Weights
https://arxiv.org/abs/1807.05076
We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning. Our model learns jointly to represent data and to bind class labels to representations in a single shot. It builds representations via slow weights, learned across tasks through SGD, while fast weights constructed by a Hebbian learning rule implement one-shot binding for each new task. On the Omniglot, Mini-ImageNet, and Penn Treebank one-shot learning benchmarks, our model achieves state-of-the-art results.
[1807.05118] Tune: A Research Platform for Distributed Model Selection and Training
https://arxiv.org/abs/1807.05118
Modern machine learning algorithms are increasingly computationally demanding, requiring specialized hardware and distributed computation to achieve high performance in a reasonable time frame. Many hyperparameter search algorithms have been proposed for improving the efficiency of model selection, however their adaptation to the distributed compute environment is often ad-hoc. We propose Tune, a unified framework for model selection and training that provides a narrow-waist interface between training scripts and search algorithms. We show that this interface meets the requirements for a broad range of hyperparameter search algorithms, allows straightforward scaling of search to large clusters, and simplifies algorithm implementation. We demonstrate the implementation of several state-of-the-art hyperparameter search algorithms in Tune. Tune is available at this http URL
[1807.05027] Are generative deep models for novelty detection truly better?
https://arxiv.org/abs/1807.05027
Many deep models have been recently proposed for anomaly detection. This paper presents comparison of selected generative deep models and classical anomaly detection methods on an extensive number of non--image benchmark datasets. We provide statistical comparison of the selected models, in many configurations, architectures and hyperparamaters. We arrive to conclusion that performance of the generative models is determined by the process of selection of their hyperparameters. Specifically, performance of the deep generative models deteriorates with decreasing amount of anomalous samples used in hyperparameter selection. In practical scenarios of anomaly detection, none of the deep generative models systematically outperforms the kNN.
[1807.04950] Deep Learning in the Wild
https://arxiv.org/abs/1807.04950
Deep learning with neural networks is applied by an increasing number of people outside of classic research environments, due to the vast success of the methodology on a wide range of machine perception tasks. While this interest is fueled by beautiful success stories, practical work in deep learning on novel tasks without existing baselines remains challenging. This paper explores the specific challenges arising in the realm of real world tasks, based on case studies from research & development in conjunction with industry, and extracts lessons learned from them. It thus fills a gap between the publication of latest algorithmic and methodical developments, and the usually omitted nitty-gritty of how to make them work. Specifically, we give insight into deep learning projects on face matching, print media monitoring, industrial quality control, music scanning, strategy game playing, and automated machine learning, thereby providing best practices for deep learning in practice.
[1805.02556] Skeleton-Based Relational Modeling for Action Recognition
https://arxiv.org/abs/1805.02556
With the fast development of effective and low-cost human skeleton capture systems, skeleton-based action recognition has attracted much attention recently. Most existing methods use Convolutional Neural Network(CNN) and Recurrent Neural Network(RNN) to extract spatio-temporal information embedded in the skeleton sequences for action recognition. However, these approaches are limited in the ability of relational modeling in a single skeleton, due to the loss of important structural information when converting the raw skeleton data to adapt to the CNN or RNN input. In this paper, we propose an Attentional Recurrent Relational Network-LSTM(ARRN-LSTM) to simultaneously model spatial configurations and temporal dynamics in skeletons for action recognition. The spatial patterns embedded in a single skeleton are learned by a Recurrent Relational Network, followed by a multi-layer LSTM to extract temporal features in the skeleton sequences. To exploit the complementarity between different geometries in the skeleton for sufficient relational modeling, we design a two-stream architecture to learn the relationship among joints and explore the underlying patterns among lines simultaneously. We also introduce an adaptive attentional module for focusing on potential discriminative parts of the skeleton towards a certain action. Extensive experiments are performed on several popular action recognition datasets and the results show that the proposed approach achieves competitive results with the state-of-the-art methods.
【UMAP降维：均匀流形逼近与投影】《UMAP Uniform Manifold Approximation and Projection for Dimension Reduction | SciPy 2018 - YouTube》 O网页链接
《Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning》D M Nguyen, E Tsiligianni, R Calderbank, N Deligiannis [Vrije Universiteit Brussel & Duke University] (2018) O网页链接 view:O网页链接
《A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks》K Lee, K Lee, H Lee, J Shin [Korea Advanced Institute of Science and Technology (KAIST) & University of Michigan] (2018) O网页链接 view:O网页链接
《Variance Reduction for Reinforcement Learning in Input-Driven Environments》H Mao, S B Venkatakrishnan, M Schwarzkopf, M Alizadeh [MIT] (2018) O网页链接 view:O网页链接
《Anytime Neural Prediction via Slicing Networks Vertically》H Lee, J Shin [Korea Advanced Institute of Science and Technology] (2018) O网页链接 view:O网页链接
《A Single Shot Text Detector with Scale-adaptive Anchors》Q Yuan, B Zhang, H Li, Z Wang, Z Luo (2018) O网页链接 view:O网页链接
《Contextual Bandits under Delayed Feedback》C Vernade, A Carpentier, G Zappella, B Ermis, M Brueckner [Amazon & Otto-Von-Guericke Universität] (2018) O网页链接 view:O网页链接
《A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation》Y Hu, A Soltoggio, R Lock, S Carter [Loughborough University & The ICE Agency] (2018) O网页链接 view:O网页链接
《Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network》Fanny, T W Cenggoro [Bina Nusantara University] (2018) O网页链接 view:O网页链接
《Scalable Recommender Systems through Recursive Evidence Chains》E Tragas, C Luo, M Gazeau, K Luk, D Duvenaud [Snapchat & University of Toronto & Borealis AI] (2018) O网页链接 view:O网页链接
《Learning Theory and Algorithms for Revenue Management in Sponsored Search》L Wang, H Liu, G Chen, S Ren, X Meng, Y Hu [Alibaba Group] (2018) O网页链接 view:O网页链接
《3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data》M Weiler, M Geiger, M Welling, W Boomsma, T Cohen [University of Amsterdam & EPFL] (2018) O网页链接 view:O网页链接 GitHub:O网页链接
《Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes》R Fruit, M Pirotta, A Lazaric [Inria Lille & Facebook AI Research] (2018) O网页链接 view:O网页链接
《Automatic deep learning-based normalization of breast dynamic contrast-enhanced magnetic resonance images》J Zhang, A Saha, B J. Soher, M A. Mazurowski [Duke University] (2018) O网页链接 view:O网页链接 GitHub:O网页链接
《Automated Vulnerability Detection in Source Code Using Deep Representation Learning》R L. Russell, L Kim, L H. Hamilton, T Lazovich, J A. Harer, O Ozdemir, P M. Ellingwood, M W. McConley [Draper] (2018) O网页链接 view:O网页链接
《Subpixel-Precise Tracking of Rigid Objects in Real-time》T Böttger, M Ulrich, C Steger [MVTec Software] (2018) O网页链接 view:O网页链接
【SciPy 2018视频专辑】《SciPy 2018: Scientific Computing with Python Conference - YouTube》 O网页链接
【将语言、视觉与行为联系起来】《Connecting Language and Vision to Actions(ACL 2018 Tutorial)》 O网页链接
《Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning》D M Nguyen, E Tsiligianni, R Calderbank, N Deligiannis [Vrije Universiteit Brussel & Duke University] (2018) O网页链接 view:O网页链接
《MAT-CNN-SOPC: Motionless Analysis of Traffic Using Convolutional Neural Networks on System-On-a-Programmable-Chip》S Dey, G Kalliatakis, S Saha, A K Singh, S Ehsan, K McDonald-Maier [University of Essex] (2018) O网页链接 view:O网页链接
《MAT-CNN-SOPC: Motionless Analysis of Traffic Using Convolutional Neural Networks on System-On-a-Programmable-Chip》S Dey, G Kalliatakis, S Saha, A K Singh, S Ehsan, K McDonald-Maier [University of Essex] (2018) O网页链接 view:O网页链接
————————————————————
图神经网络+池化模块，斯坦福等提出层级图表征学习 | 机器之心
https://www.jiqizhixin.com/articles/2018-07-16-3
————————————————————
获7000万元融资之后，一知智能要把自然语言处理技术吃透 | 机器之心
https://www.jiqizhixin.com/articles/2018-07-16-5
获7000万元融资之后，一知智能要把自然语言处理技术吃透
日前，杭州一知智能科技有限公司宣布在 2018 年 7 月完成 A 轮融资，融资金额 7000 万元人民币。本轮融资由启赋资本领投、金沙江联合资本等机构跟投。资金主要用于进一步加强人工智能 NLP 人才引进和核心技术科研投入，并推出基于 NLP 技术的智能外呼机器人。
赵洲-浙江大学个人主页
http://person.zju.edu.cn/zhaozhou/686052.html
zjuzhaozhou (Zhao Zhou)
https://github.com/zjuzhaozhou
赵洲副教授 — 浙江大学DCD实验室
http://www.dcd.zju.edu.cn/62105458/8d756d32526f65596388
2018机器阅读理解技术竞赛，奇点机智获第一名 - CSDN博客
https://blog.csdn.net/dqcfkyqdxym3f8rb0/article/details/80440773
科大讯飞认知智能持续突破，机器阅读理解SQuAD测试勇夺第一！
http://www.iflytek.com/content/details_135_2411.html
获7000万元融资之后，一知智能要把自然语言处理技术吃透 | 机器之心
https://www.jiqizhixin.com/articles/2018-07-16-5
富士康郭台铭现身斯坦福大学，谈工业人工智能，创立人工智能子公司 | 机器之心
https://www.jiqizhixin.com/articles/2018-07-16-4
face-api.js：一个在浏览器中进行人脸识别的 JavaScript 接口 | 机器之心
https://www.jiqizhixin.com/articles/2018-07-16-2