Machine Learning and Artificial Neural Networks
Machine learning is needed for a wide range of important applications that become more and more essential for the modern society: text-based web search, image-based web search, movie search, cognitive robotics, mobile robotics and self-driving cars, embedded computing, pattern recognition, image recognition, voice recognition, speech recognition, handwriting recognition, video surveillance, scientific computing, scheduling, optimization, artificial intelligence etc.

Our research activities cover fundamental topics related to machine learning: Bayesian / probabilistic reasoning; hidden Markov models; expectation maximization; feedforward neural networks; recurrent neural networks; support vector machines; reinforcement learning; artificial evolution, unsupervised learning techniques, data mining, pattern classification and regression, empirical evaluation, feature selection, discretization, combining multiple models, data fusion, cluster analysis.

Our team of researchers has produced world-leading research in many of the fields mentioned above and, so far,  they have won nine international competitions on various problems (e.g. on classification, object detection, segmentation) applied to different fields such as mitosis detection, brain image segmentation, traffic sign recognition, chinese and arabic handwriting competition, and so on.


  • Business Engineering and Production
  • Energy and Environment
  • Industrial Technologies
  • Information and Communication Technologies