I am a research scientist at RISE AI (Research institutes Sweden).
March 23, 2018, I defended my PhD thesis, Representation learning for natural language (click for details). The last five years, I have spent as a PhD student in the machine learning research group at Chalmers university of technology, working on deep learning and natural language processing. I have worked on summarization, dialogue systems, adversarial training, and character-based RNNs for sequence labeling and morphological analogies. I am also interested in convnets for language and policy gradient methods.
I tweet and blog about things I find interesting, and give talks in our popular seminar series at the department and other events. During 2016-2017, I was the organizer of the seminar series. Most of my recent code is written in Python with Pytorch, and I am also familiar with Tensorflow, 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.
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.
Furthermore, I have taught the following courses.
During 2016-217, I was the organizer of Chalmer Machine Learning Seminars.
When not doing research or teaching, I am a long distance runner and the lucky father of two wonderful children.