Abstract: 

At the Intelligent and Interactive Systems (IIS) of the University of Innsbruck, our motto is “Making robots learn to perceive and act with understanding”. My main research area in the group is focused in learning and perception. In this talk I will show my recent research over the past few years, which covers fundamental machine learning in the areas of layer pruning and autotune algorithms where we evaluate the batch-entropy which quantifies the flow of information through each layer of a neural network. My work is applied on different domains such as vision and robotics. In vision I have studied the applicability of deep learning for concept learning, such as in the cases of associative and relative concepts as well as applied to more specific domains such as medical image and video analysis. For this talk, I will focus in this later case and show how the research we develop at IIS is being currently applied through different collaborations with the Medical University of Innsbruck, covering the labeling of anatomical structures in surgical videos, extracting new knowledge from EEG data or filling missing informationin incomplete DNA data.

Bio:
Antonio Rodríguez-Sánchez is currently an Assistant Professor in the Intelligent and Interactive Systems group of the department of Computer Science at the Universität Innsbruck (Austria) leaded by Prof. Justus Piater. He was born in Santiago de Compostela (A Coruña), a beautiful city in the north-west of Spain. He completed his Ph.D. at the Center for Vision Research (York University, Toronto, Canada) on modeling attention and intermediate areas of the visual cortex under the supervision of Prof. John K. Tsotsos (Canada Research Chair) in 2010. His current research interests include different areas of artificial intelligence: Computational neuroscience, (deep) neural networks, computer vision, machine learning and robotics.