This page in Swedish

Martin Längkvist

Title: Researcher School/office: School of Science and Technology

Email:

Phone: +46 19 303749

Room: T2235

Martin Längkvist

About Martin Längkvist

I am a post-doc at the Machine Perception and Interaction Lab at AASS Research Center, Department of Science and Technology, Örebro University, Sweden. I received my Ph.D in Computer Science in Örebro in 2015.

My research interest is in machine learning, specifically learning good representations from raw sensory data. I believe finding good representations is the key to designing a system that can solve interesting challenging real-world problems, go beyond human-level intelligence, and ultimately explain complicated data for us that we don't understand. In order to achieve this, I envision a learning algorithm that can learn feature representations from both unlabeled and labeled data, be guided with and without human interaction, and that are on different levels of abstractions in order to bridge the gap between low-level sensory data and high-level abstract concepts.

You can find more about my research and publications at my Google Profile Page or Research Gate Page or Personal Academic Website

Publications

Articles in journals |  Articles, reviews/surveys |  Conference papers |  Doctoral theses, comprehensive summaries | 

Articles in journals

Alirezaie, M. , Kiselev, A. , Längkvist, M. , Klügl, F. & Loutfi, A. (2017). An Ontology-Based Reasoning Framework for Querying Satellite Images for Disaster Monitoring. Sensors, 17 (11).
Persson, A. , Längkvist, M. & Loutfi, A. (2017). Learning Actions to Improve the Perceptual Anchoring of Object. Frontiers in Robotics and AI, 3 (76).
Längkvist, M. & Loutfi, A. (2015). Learning feature representations with a cost-relevant sparse autoencoder. International Journal of Neural Systems, 25 (1), 1450034.
Kumar Mani, G. , Sankar, P. , Längkvist, M. , Loutfi, A. & Rayappan, J. B. B. (2014). Detection of spoiled meat using an electronic nose. Sensors.
Längkvist, M. , Loutfi, A. & Karlsson, L. (2014). Selective attention auto-encoder for automatic sleep staging. Biomedical Signal Processing and Control.
Längkvist, M. , Coradeschi, S. , Loutfi, A. & Rayappan, J. B. B. (2013). Fast Classification of Meat Spoilage Markers Using Nanostructured ZnO Thin Films and Unsupervised Feature Learning. Sensors, 13 (2), 1578-1592.
Längkvist, M. , Karlsson, L. & Loutfi, A. (2012). Sleep stage classification using unsupervised feature learning. Advances in Artificial Neural Systems, 107046.

Articles, reviews/surveys

Längkvist, M. , Karlsson, L. & Loutfi, A. (2014). A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognition Letters, 42 (1), 11-24.

Conference papers

Längkvist, M. , Alirezaie, M. , Kiselev, A. & Loutfi, A. (2016). Interactive Learning with Convolutional Neural Networks for Image Labeling. In: International Joint Conference on Artificial Intelligence (IJCAI). Paper presented at International Joint Conference on Artificial Intelligence (IJCAI), New York, USA, 9-15th July, 2016.
Alirezaie, M. , Längkvist, M. , Kiselev, A. & Loutfi, A. (2016). Open GeoSpatial Data as a Source of Ground Truth for Automated Labelling of Satellite Images. In: Krzysztof Janowicz et al., SDW 2016 Spatial Data on the Web, Proceedings. Paper presented at The 9th International Conference on Geographic Information Science (GIScience 2016), Montreal, Canada, September 27-30, 2016 (pp. 5-8). CEUR Workshop Proceedings.
Längkvist, M. & Loutfi, A. (2012). Learning Representations with a Dynamic Objective Sparse Autoencoder. Paper presented at Neural Information Processing Systems.
Längkvist, M. & Loutfi, A. (2012). Not all signals are created equal: Dynamic objective auto-encoder for multivariate data. Paper presented at NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2012.
Längkvist, M. & Loutfi, A. (2011). Unsupervised feature learning for electronic nose data applied to Bacteria Identification in Blood.. Paper presented at NIPS 2011 Workshop on Deep Learning and Unsupervised Feature Learning.

Doctoral theses, comprehensive summaries

Längkvist, M. (2014). Modeling time-series with deep networks. (Doctoral dissertation). (Comprehensive summary) Örebro: Örebro university.