Deep Neural Networks for High Dimension, Low …

Deep Neural Networks for High Dimension, Low Sample Size Data Bo Liu, Ying Wei, Yu Zhang, Qiang Yang Hong Kong University of Science and Technology, Hong Kong

  High, Network, Dimensions, Deep, Neural, Deep neural networks for high dimension

Training Feedforward Neural Networks Using …

Training Feedforward Neural Networks Using Genetic Algorithms David J. Montana and Lawrence Davis BBN Systems and Technologies Corp. 10 Mouiton St.

  Genetic, Algorithm, Neural, Genetic algorithms, Feedforward neural, Feedforward

Learning Feature Engineering for Classification

Given a set of features and class labels, the classiÞer ... c!T of arityr, an ordered list of features[f i,...,f i+r ! 1] and a usefulness score. ... paradigm for each combination and selects top-useful ones.k In the following section, we describe how LFE learns and

  Feature, Class

Imaging Time-Series to Improve Classification and Imputation

iis the time stamp and Nis a con-stant factor to regularize the span of the polar coordinate sys-tem. This polar coordinate based representation is a novel way to understand time series. As time increases, correspond-ing values warp among different angular points on the span-ning circles, like water rippling. The encoding map of equa-

  Series, Time, Improves, Imaging, Imaging time series to improve

Recurrent Neural Network for Text Classification with ...

Figure 2: Three architectures for modelling text with multi-task learning. Motivated by the success of multi-task learning [Caruana, 1997], we propose three multi-task models to leverage super-vised data from many related tasks. Deep neural model is well suited for multi-task learning since the features learned from a task may be useful for ...

  Network, Texts, Learning, Neural, Recurrent, Recurrent neural network for text

Deep Matrix Factorization Models for Recommender Systems

Deep Matrix Factorization Models for Recommender Systems Hong-Jian Xue, Xin-Yu Dai, Jianbing Zhang, Shujian Huang, Jiajun Chen National Key Laboratory for Novel Software Technology; Nanjing University, Nanjing 210023, China

L2,1-Norm Regularized Discriminative Feature Selection …

rithms, e.g., Fisher score [Duda et al., 2001] , robust regres-sion [Nie et al., 2010], sparse multi-output regression [Zhao et al., 2010] and trace ratio [Nie et al., 2008], usually select featuresaccordingto labels of the training data. Because dis-criminative informationis enclosed in labels, supervised fea-

  Feature, Selection, Norm, Discriminative, Dudas, Norm regularized discriminative feature selection, Regularized

DeepFM: A Factorization-Machine based Neural Network …

DeepFM: A Factorization-Machine based Neural Network for CTR Prediction Huifeng Guo 1, Ruiming Tang2, Yunming Yey1, Zhenguo Li2, Xiuqiang He2 1Shenzhen Graduate School, Harbin Institute of Technology, China 2Noah's Ark Research Lab, Huawei, China 1huifengguo@yeah.net, yeyunming@hit.edu.cn,2ftangruiming, li.zhenguo, hexiuqiangg@huawei.com Abstract Learning …

  Based, Network, Machine, Neural, Factorization, Deepfm, A factorization machine based neural network

Detecting Rumors from Microblogs with Recurrent Neural ...

Detecting Rumors from Microblogs with Recurrent Neural Networks Jing Ma,1 Wei Gao,2 Prasenjit Mitra,2 Sejeong Kwon,3 Bernard J. Jansen,2 Kam-Fai Wong,1 Meeyoung Cha3 1The Chinese University of Hong Kong, Hong Kong SAR 2Qatar Computing Research Institute, Hamad Bin Khalifa University, Qatar 3Graduate School of Culture Technology, Korea Advanced …

  Detecting

Time-Aware Multi-Scale RNNs for Time Series Modeling

of genres requires modeling the emotional changes in music, which are controlled by note duration. Therefore, different scales are also needed at different time steps as the notes have different durations at different times [Hu et al., 2019]. Recently, some methods have been proposed to select ap-propriate scales corresponding to each sample ...

  Green, Music

Abstract arXiv:1411.4038v2 [cs.CV] 8 Mar 2015

networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolu-tional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet ...

  Network, Tional, Convolu tional networks, Convolu

Siamese Neural Networks for One-shot Image Recognition

Several factors make convolutional networks especially ap-pealing. Local connectivity can greatly reduce the num-ber of parameters in the model, which inherently provides some form of built-in regularization, although convolu-tional layers are computationally more expensive than stan-dard nonlinearities. Also, the convolution operation used in

  Network, Tional, Convolutional, Convolutional networks, Convolu

Learning Spatiotemporal Features With 3D Convolutional ...

few years in feature learning, various pre-trained convolu-tional network (ConvNet) models [16] are made available for extracting image features. These features are the activa-tions of the network’s last few fully-connected layers which perform well on …

  Tional, Convolu

Fully Convolutional Networks for Semantic Segmentation

networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolu-tional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet ...

  Network, Tional, Convolutional, Convolutional networks, Convolu tional networks, Convolu

Convolutional Neural Networks

but very effective attention module for Convolu-tional Neural Networks (ConvNets). In contrast to existing channel-wise and spatial-wise attention modules, our module instead infers 3-D atten-tion weights for the feature map in a layer with-out adding parameters to the original networks. Specifically, we base on some well-known neuro-

  Network, Tional, Convolu

Image Restoration Using Very Deep Convolutional Encoder ...

The convolu-tional layers act as the feature extractor which encode the primary components of image contents while eliminating the corruption. The deconvolutional layers then decode the image abstraction to recover the image content details. We propose to add skip connections between corresponding convolutional and deconvolu-tional layers.

  Using, Tional, Deep, Restoration, Very, Convolutional, Convolu, Restoration using very deep convolutional

Attention Augmented Convolutional Networks

Attention Augmented Convolutional Networks Irwan Bello Barret Zoph Ashish Vaswani Jonathon Shlens Quoc V. Le Google Brain {ibello,barretzoph,avaswani,shlens,qvl}@google.com Abstract Convolutional networks have been the paradigm of choice in many computer vision applications. The convolu-tion operation however has a significant weakness in that it

  Network, Convolutional, Convolutional networks, Convolu

Dilated Residual Networks - CVF Open Access

Convolutional networks were originally developed for classifying hand-written digits [9]. More recently, convolu-tional network architectures have evolved to classify much more complex images [8, 13, 14, 6]. Yet a central aspect of network architecture has remained largely in place. Convo-lutional networks for image classification ...

  Network, Tional, Residual, Convolutional, Convolutional networks, Dilated, Convos, Convolu tional networks, Convolu, Dilated residual networks, Lutional