Machine Learning Scientist
"Research is creating new Knowledge." Neil Armstrong
Siamak Mehrkanoon
Assistant Professor,
Maastricht University,
The Netherlands.
​
Hot Trends
Research
Scientific Background in multidisciplinary fields such as: Machine Learning, Deep Learning, Data Mining, Neural Networks, Computational Mathematics and Optimization.
Expert in developing advanced Machine Learning models including: Deep Learning, Domain Adaptation, Transfer Learning in Supervised/ Unsupervised/Semi-Supervised Settings.
LATEST RESEARCH
Online Semi-Supervised Clustering (I-MSS-KSC)
​
Given a few user-labeled data points the initial model is learned and then the class membership of the remaining data points in the current and subsequent time instants are estimated and propagated in an on-line fashion. Furthermore, the tracking capabilities of the Kalman filter is used to provide the labels of the objects in motion and thus regularizing the solution obtained by the MSS-KSC algorithm. An unsupervised model is used as a core model where the labels information are added via regularization terms ...
Scalable Hybrid Deep Neural Kernel Networks
​
We introduced a hybrid deep neural kernel framework. The proposed deep learning model follows a combination of neural networks based architecture and a kernel based model. In particular, here an explicit feature map is used to make the transition between the two architectures more straight-forward as well as making the model scalable to large datasets by solving the optimization problem in the primal. Experimental results show a significant improvement over shallow models on several medium to large scale real-life datasets.