Dr. Jyri Kivinen, Ph.D. (Informatics), M.Sc. (Tech.)

Selected Publications

• A Novel Variational Autoencoder with Applications to Generative Modelling, Classification, and Ordinal Regression.
  Joel Jaskari and Jyri J. Kivinen.
  arXiv e-prints, arXiv:1812.07352, December 2018.
• Statistical Models for Natural Scene Data.
  Jyri J. Kivinen.
  PhD (Informatics) Thesis, The University of Edinburgh, June 2014.
• Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection.
  Jyri J. Kivinen, Christopher K. I. Williams, and Nicolas Heess.
  In Proc., International Conference on Artificial Intelligence and Statistics (AISTATS),
  April 2014, Reykjavik, Iceland.
• Multiple Texture Boltzmann Machines.
  Jyri J. Kivinen and Christopher K. I. Williams.
  In Proc., International Conference on Artificial Intelligence and Statistics (AISTATS),
  April 2012, La Palma, Canary Islands.
• Transformation Equivariant Boltzmann Machines.
  Jyri J. Kivinen and Christopher K. I. Williams.
  In Proc., International Conference on Artificial Neural Networks (ICANN),
  June 2011, Espoo, Finland.
• Learning Multiscale Representations of Natural Scenes Using Dirichlet Processes.
  Jyri J. Kivinen, Erik B. Sudderth, and Michael I. Jordan.
  In Proc., IEEE International Conference on Computer Vision (ICCV),
  October 2007, Rio de Janeiro, Brazil.
• Image Denoising with Nonparametric Hidden Markov Trees.
  Jyri J. Kivinen, Erik B. Sudderth, and Michael I. Jordan.
  In Proc., IEEE International Conference on Image Processing (ICIP),
  September 2007, San Antonio, Texas, USA.

Recent Teaching

• Teacher-in-charge: CS-E4890 - Deep Learning, 2017.
• Teacher-in-charge: CS-E4050 - Special Course in Machine Learning and Data Science V (P), Autumn 2016 (Deep Learning).
• One of the teachers in the course: T-61.6050 - Special Course in Computer and Information Science V P, Autumn 2015 (Deep Learning).