CASI: A Convolutional Neural Network Approach for Shell Identification

We utilize techniques from deep learning to identify signatures of stellar feedback in simulated molecular clouds. Specifically, we implement a deep neural network with an architecture similar to U-Net and apply it to the problem of identifying wind-driven shells and bubbles using data from magneto-hydrodynamic simulations of turbulent molecular clouds with embedded stellar sources. The network is applied to two tasks, dense regression and segmentation, on two varieties of data, simulated density and synthetic 12 CO observations. Our Convolutional Approach for Shell Identification (CASI) is able to obtain a true positive rate greater than 90\%, while maintaining a false positive rate of 1\%, on two segmentation tasks and also performs well on related regression tasks. The source code for CASI is available on GitLab.

[1]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[2]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

[3]  A. Cattaneo.  Competition and Cooperation in Neural Nets, Vol. 45, S. Amari, M.A. Arbib (Eds.), in: Lecture Notes in Biomathematics. Springer-Verlag, Berlin, Heidelberg, New York (1982) , 1983 .

[4]  Quoc V. Le,et al.  Don't Decay the Learning Rate, Increase the Batch Size , 2017, ICLR.

[5]  Jorge Nocedal,et al.  On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima , 2016, ICLR.

[6]  Frank Hutter,et al.  CMA-ES for Hyperparameter Optimization of Deep Neural Networks , 2016, ArXiv.

[7]  Yi Ding,et al.  RUN: Residual U-Net for Computer-Aided Detection of Pulmonary Nodules without Candidate Selection , 2018, ArXiv.

[8]  Michèle Sebag,et al.  Collaborative hyperparameter tuning , 2013, ICML.

[9]  Yoshua Bengio,et al.  Residual Connections Encourage Iterative Inference , 2017, ICLR.

[10]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[11]  Kilian Q. Weinberger,et al.  Snapshot Ensembles: Train 1, get M for free , 2017, ICLR.

[12]  Carlo Luschi,et al.  Revisiting Small Batch Training for Deep Neural Networks , 2018, ArXiv.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Zhengyou Zhang,et al.  A Survey of Recent Advances in Face Detection , 2010 .

[15]  Mert R. Sabuncu,et al.  3D Convolutional Neural Networks for Classification of Functional Connectomes , 2018, DLMIA/ML-CDS@MICCAI.

[16]  B. Póczos,et al.  CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding , 2017, Monthly Notices of the Royal Astronomical Society.

[17]  Xiaohui Xie,et al.  AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy , 2018, Medical physics.