Time Series Super Resolution withTemporal Adaptive Batch Normalization

In many machine learning problems, data is naturally expressed as a time series. 1 Here, we introduce a deep neural network architecture for reconstructing a high2 resolution time series signal from low-resolution measurements, a task that we 3 call time series super resolution. Central to our architecture is a novel temporal 4 adaptive normalization layer that combines the strength of convolutional and 5 recurrent approaches. We apply our model to diverse super resolution problems: 6 audio super-resolution and the enhancement of functional genomics assays. In 7 each case, our method significantly outperforms strong baselines, demonstrating 8 its ability to solve practical problems in a wide range of domains. 9

[1]  Yoshua Bengio,et al.  SampleRNN: An Unconditional End-to-End Neural Audio Generation Model , 2016, ICLR.

[2]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Jonathon Shlens,et al.  A Learned Representation For Artistic Style , 2016, ICLR.

[4]  Vincent Dumoulin,et al.  Deconvolution and Checkerboard Artifacts , 2016 .

[5]  Aaron C. Courville,et al.  FiLM: Visual Reasoning with a General Conditioning Layer , 2017, AAAI.

[6]  A. Gray,et al.  Distance measures for speech processing , 1976 .

[7]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Manolis Kellis,et al.  Large-scale epigenome imputation improves data quality and disease variant enrichment , 2015, Nature Biotechnology.

[9]  Daniel Rueckert,et al.  Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Stefano Ermon,et al.  Amortized Variational Compressive Sensing , 2018 .

[11]  Michael Q. Zhang,et al.  Integrative analysis of 111 reference human epigenomes , 2015, Nature.

[12]  Serge J. Belongie,et al.  Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[13]  Anshul Kundaje,et al.  Denoising genome-wide histone ChIP-seq with convolutional neural networks , 2016, bioRxiv.

[14]  Dan Xie,et al.  Extensive Variation in Chromatin States Across Humans , 2013, Science.

[15]  Anshul Kundaje,et al.  Denoising Genome-wide Histone ChIP-seq with Convolutional Neural Networks , 2016 .

[16]  Per Ekstrand.  BANDWIDTH EXTENSION OF AUDIO SIGNALS BY SPECTRAL BAND REPLICATION , 2002 .

[17]  David Minnen,et al.  Variable Rate Image Compression with Recurrent Neural Networks , 2015, ICLR.

[18]  Chin-Hui Lee,et al.  DNN-based speech bandwidth expansion and its application to adding high-frequency missing features for automatic speech recognition of narrowband speech , 2015, INTERSPEECH.