Fork me on GitHub

About me

I am a PhD student in the machine learning research group working on deep learning and natural language processing. Tasks include summarization, dialogue systems, and sequence labeling, and lately I have been looking at adversarial training and policy gradient methods.

I find attention models and neural machine translation fascinating, and listen to the Talking Machines podcast every two weeks.

I tweet and blog about things I find interesting, and give talks in our popular seminar series at the department and other events. Most of my recent code is written in Python with Tensorflow, and I have some familiarity with Theano and Lasagne.

My Licentiate Thesis, titled "Multi-Document Summarization and Semantic Relatedness", was defended on November 20th, 2015. Tapani Raiko from Aalto University was discussion leader. Read more about this. My master's thesis was about small-world network models in realistically geographical settings. Read more about this.

Teaching

During period four (March-May 2016), I developed and taught a PhD course in Deep Learning, together with Mikael Kågebäck and Fredrik Johansson. The course covered some of the most important topics in the field, including convolutional neural networks, recurrent neural networks, unsupervised methods, and regularization techniques. We used a “flipped classroom” approach, with video lectures from some of the best researchers in the field, along with discussion sessions. Read more at the course web page.

I also supervise a number of master students.

I have also taught the following courses.

Other things

I am the organizer of Chalmer Machine Learning Seminars. Get in touch if you want to know more about this! Or just take a look at the scheduled talks and show up!

I'm working in the project Data-Driven Secure Bussiness Intelligence, grant IIS11-0089 from the Swedish Foundation for Strategic Research (SSF). We have a nice collaboration with representatives from the industry on problems related to natural language processing and inference. Recorded Future, Seal, and Findwise are some of the companies we have worked with. Peter Damaschke and Devdatt Dubhashi are my supervisors.

When not doing research or teaching, I am a long distance runner and the lucky father of two wonderful children.

Contact

Visiting: Room 6447, EDIT building, Campus Johanneberg.
Email: first name at last name dot one.
Telephone: +46-703-969624.
Follow me on LinkedIn, Twitter, or RSS.

Olof Mogren, Department of Computer Science and Engineering, Chalmers University of Technology

LinkedIn Twitter Atom/RSS Feed