Pablo M. Olmos


Research interests

My research interests are in the area of digital communications and machine learning. Currently, I work on the following problems:

  • Analysis and design of finite-length SC-LDPC codes and Generalized LDPC codes.

  • Expectation Consistency methods for Approximate Inference in Probabilistic Graphical Models.

  • Neural Variatonal Inference and Deep Generative Models.

  • Topic Modeling and Text Recognition in Historical Documents.

Latest news!

Paper accepted at ICFHR (May 2018)

Boosting Handwriting Text Recognition in Small Databases with Transfer Learning. José Carlos Aradillas, Juan José Murillo-Fuentes, Pablo M. Olmos

Paper submitted to NIPS (May 2018)

Handling Incomplete Heterogeneous Data using VAEs. Alfredo Nazábal, Pablo M. Olmos, Zoubin Ghahramani, Isabel Valera

Pre-print uploaded (May 2018)

What are GANs useful for?. Briland Hitaj, Pablo M. Olmos, Paolo Gasti, Giuseppe Ateniese, Fernando Pérez-Cruz

Tensor Flow Course updated (February 2018)

I have added a new section on Amortized Variational Inference with Neural Networks and Variational Autoencoders.

You can find the material in the ML courses section.

New course: Introduction to Data Science and Machine Learning (January 2018)

I share the material I am preparing for an introductory course on Data Science and Machine Learning.

You can find the material in the ML courses section.