AIN Gruppe

Publikationen

  • A. D’Isanto, S. Cavuoti, F. Gieseke, K. L. Polsterer. Efficient feature selection and interpretation for photometric redshifts. A&A, 2018
  • J. R. Maat, N. Gianniotis, P. Protopapas. Efficient Optimization of Echo State Networks for Time Series Datasets. IJCNN 2018
  • F. Gieseke, K. L. Polsterer, A. Mahabal A, C. Igel, T. Heskes. Massively-parallel best subset selection for ordinary least-squares regression. SSCI, 2017
  • N. Gianniotis. Linear dimensionality reduction for time series. ICONIP, 2017
  • A. D’Isanto, K. L. Polsterer. Photometric redshift estimation via deep learning. Generalized and pre-classification-less, image based, fully probabilistic redshifts. Astron. Astrophys. 2017
  • D’Isanto A, Polsterer KL. Uncertain photometric redshifts via combining deep convolutional and mixture density networks. ESANN 2017
  • K. L. Polsterer. Astroinformatics; a new discipline or business as usual? In “Astronomical Data Analysis Software and Systems XXVII (ADASS XXVII)”, 2017 vol. 496
  • K. L. Polsterer. Photometric redshift estimations. In “Astroinformatics” 2017 vol. 325
  • S.D. Kuegler, N. Gianniotis, K. L. Polsterer. A Spectral model for multimodal redshift estimation. IEEE Symposium on Computational Intelligence and Data Mining, SSCI, 2016
  • K. L. Posterer, F. Gieseke, C. Igel, B. Doser, N. Gianniotis. Parallelized rotation and flipping INvariant Kohonen maps (PINK) on GPUs. ESANN  2016
  • K. L. Polsterer. Uncertain Multimodal Photometric Redshift Estimations. IAU Symp. Astroinformatics 2016 325
  • K.L. Polsterer, F. Gieseke. Probability density functions for astronomy. In “Astronomical Data Analysis Software an Systems XXV (ADASS XXV)” 2016 vol. 496
  • N. Gianniotis, S.D. Kuegler, K. L. Polsterer. Model-coupled autoencoder for time series visualisation. Neurocomputing  2016.
  • N. Gianniotis, C. Schnörr, C. Molkenthin, Bora SS. Approximate variational inference based on a finite sample of gaussian latent variables. Pattern Analysis Appl. 2016
  • S.D. Kuegler, N. Gianniotis, K. L. Polsterer. An explorative approach for inspecting Kepler data. MNRAS 2015
  • S.D. Kuegler, N. Gianniotis, K. L. Polsterer. Featureless classification of light curves. MNRAS 2015
  • N. Gianniotis, S.D. Kuegler, P. Tino, K. L. Polsterer, R. Misra: Autoencoding time series for visualisation. ESANN 2015
  • K. L. Polsterer, F. Gieseke, and C. Igel. Automatic classification of galaxies via machine learning techniques. In Astronomical Data Analysis Software and Systems XXIV, Astronomical Society of the Pacific Conference Series, 2014.
  • S. D. Kügler, K. Nilsson, J. Heidt, J. Esser, and T. Schultz. Properties of optically selected BL Lacertae candidates from the SDSS. AAP, 569:A95, 2014
  • P. Buschkamp, W. Seifert, K. L. Polsterer, J. Heidt, S. Rabien, H. Gemperlein, R. Genzel, M. Lehmitz, A. Pramskiy, W. Raab, D. Thompson, M De La Pena, and J. Ziegleder.  LUCI 2 : binocular and LGS/NGS AO modes of LUCI at LBT. SPIE 2014.
  • F. Gieseke, K. L. Polsterer, C. E. Oancea, and C. Igel. Speedy greedy feature selection: Better redshift estimation via massive parallelism. ESANN 2014
  • K. L. Polsterer, F. Gieseke, C. Igel, and T. Goto. Improving the performance of photometric regression models via massive parallel feature selection. In N. Manset and P. Forshay, editors, Astronomical Data Analysis Software and Systems XXIII, volume 485 of Astronomical Society of the Pacific Conference Series, page 425, 2014.
  • J. Heinermann, O. Kramer, K. L. Polsterer, and F. Gieseke. On GPU-based nearest neighbor queries for large-scale photometric catalogs
    in astronomy. KI, pages 86–97, 2013
  • O. Kramer, F. Gieseke, and K. L. Polsterer. Learning morphological maps of galaxies with unsupervised regression. Expert Systems with Applications, 2013
  • K. L. Polsterer, P. C. Zinn, and F. Gieseke. Finding new high-redshift quasars by asking the neighbours. MNRAS, 2013.

Klicken Sie hier um zur $s Seite zu gelangen.