Maureen van Eijnatten is an assistant professor of Biomedical Engineering, Medical Image Analysis and EAISI Health at Eindhoven Technical University.

Abstract: 

Deep learning can be used to automate or augment various image-guided treatments and therefore has the potential to open up completely new avenues to personalize patient treatments. This lecture will highlight some of these opportunities in maxillofacial and oncologic surgery. In addition, remaining challenges in this quickly developing field will be addressed. How can we acquire sufficient amounts of labeled (imaging) data to train deep learning models? What is the most efficient training strategy? And how can we incorporate these novel computational methods in the standard clinical workflow?

Mark Hoogendoorn, Full Professor of Artificial Intelligence, VU, Amsterdam

In healthcare many of the decisions made are of a sequential nature. Just think of a doctor continuously modifying the ventilator of an intubated ICU patient or changing the dosage of fluids administered depending on how the patient is doing. Such decision can be supported by AI-driven models. Reinforcement Learning (RL) is a very natural fit, however it comes with some characteristics that do not fit the medical domain well. In this talk, I will focus on three algorithmic innovations we have made to improve the applicability of RL in the health domain: (1) sample efficient RL; (2) safe RL with domain knowledge, and (3) explainable RL. I will explain the algorithmic improvements, and also show how we have applied these in the health domain. 

Unfortunately there is no video of this colloquium. We do have presentation slides.

Hayley Hung, Associate Professor at the Technical University of Delft. She leads the Perceptive Computing Lab, which is part of the Pattern Recognition and Bioinformatics Group.

Humans interact with one another on a daily basis. Social bonding is a key component in human collaboration and with it, comes the possibility to achieve more as a group than as an individual. In today's society, one can consider social bonding to be important in relationships with a romantic partner, friends , and family or with professional colleagues. Studying how social interactions unfold and how these can affect or enhance social relationships taps into human's instinctive perception of the experience of social interactions. While the text above may sound like the start of a social science presentation, in this talk, Hung argued that in order to enhance the quality of human social experience where it could have the greatest benefit, we need an inherently interdisciplinary approach combining both social science and computer science. The drive for an interdisciplinary approach stems a lot from the idea that computational tools that could have the most impact for enhancing social experience must necessarily be embedded in people's everyday lives. Fortunately, with the rising popularity of wearable technologies, there is an opportunity to digitize momentary social experiences as they unfold in the real world.

However, when we step away from more restrictive social settings to cases where people are free to move around as they wish, most research (stemming from the ubiquitous and pervasive computing community ) have tended to apply proxies such as co-location as a measure of social interaction. This approach strips away the possibility of measuring interaction quality, pushing the research focus more towards larger scale sociological studies that try to find generalisable patterns of human behaviour and its relation with their affective experience. In this talk, Hung argued that human experience has an inherently personal component that should be explored if we want to close the loop on enhancing the quality of human social experience. This starts by first reconsidering traditional approaches to measuring human affective experience. Through examples from her prior work, Hung demonstrated that this provides intriguing new opportunities for investigating unconventional approaches to multimodal data processing which opens up a new field re-exploring phenomena from a machine perspective that goes beyond the commonly understood modalities of sight, and hearing.

Hung concludes the talk by discussing open opportunities regarding new directions of potential research on social experience monitoring and enhancement with respect to topics such as privacy, data labelling, personalisation, and multimodal experience enhancement.

Rob van der Mei, CWI and Vrije Universiteit Amsterdam

In life-threatening situations where every second counts, the timely presence of emergency services can make the difference the survival or death.  

In this talk, I will give a number of examples of success stories where data analytics, stochastics modeling and optimization have been successfully applied in real-life practice. In doing so, I will also address challenges involved in bringing academic research results to practice. 

Peter Flach, Professor of Artificial Intelligence at the University of Bristol

Abstract:
Our understanding of performance evaluation measures for machine-learned classifiers has improved considerably over the last decades. However, there is a range of areas where this understanding is still lacking, leading to ill-advised practices in classifier evaluation. This is clearly problematic, since if machine learning researchers are unclear about what exactly their experiments are telling them about their machine learning algorithms, then how can end-users trust systems deploying those algorithms?  

I suggest that in order to make further progress we need to develop a proper measurement theory of machine learning. Measurement theory studies the concepts of measurement and scale. If one has a way to measure, say, the length of individual rods or planks, this should also allow one to then calculate the combined length of concatenated rods or planks. What relevant concatenation operations are there in data science and AI, and what does that mean for the underlying measurement scale?

I discuss by example what such a measurement theory might look like and what kinds of new results it would entail. I furthermore argue that key properties such as classification ability and data set difficulty are unlikely to be directly observable, suggesting the need for latent-variable models. Ultimately, machine learning experiments need to go beyond simple correlations and aim to make causal inferences of the form 'Algorithm A outperformed algorithm B because the classes were highly imbalanced', or counterfactually, 'if the classes were re-balanced, this performance difference between A and B would not have been observed'. 

Short CV:
Peter Flach has been Professor of Artificial Intelligence at the University of Bristol since 2003. An internationally leading scholar in the evaluation and improvement of machine learning models using ROC analysis and calibration, he has also published on mining highly structured data, and has an interest in human-centred AI. He is author of Simply Logical: Intelligent Reasoning by Example (John Wiley, 1994) and Machine Learning: the Art and Science of Algorithms that Make Sense of Data (Cambridge University Press, 2012).

Prof Flach stepped down last year as the Editor-in-Chief of the Machine Learning journal, after being in post for 10 years. He was Programme Co-Chair of the 1999 International Conference on Inductive Logic Programming, the 2001 European Conference on Machine Learning, the 2009 ACM Conference on Knowledge Discovery and Data Mining, and the 2012 European Conference on Machine Learning and Knowledge Discovery in Databases in Bristol. He is President of the European Association for Data Science, and a Fellow of the Alan Turing Institute for Data Science and Artificial Intelligence. 

Javier Alonso Mora, Associate Professor of Delft University of Technology

Francesca Ieva, Senior Researcher Involved in Healthcare and Education Research

Harrie Oosterhuis, assistant professor at the Data Science Group of the Institute of Computing and Information Sciences (iCIS) of Radboud University.

Ozan Öktem, Department of Mathematics, KTH - Royal Institute of Technology OF VAN UPPSALA

Ronals Geskus, Associate Professor at the University of Oxford

Joaquin Vanschoren, Assistant Professor of Machine Learning at the Eindhoven University of Technology (TU/e).

Kristian Kersting, Kristian Kersting is a Full Professor at the Computer Science Department of the TU Darmstadt University, Germany.

Max Welling,  Research Chair in Machine Learning at the University of Amsterdam and Distinguished Scientist at MSR.

Bernet Elzinga, Professor of Stress-related Psychopathology

Wouter van Loon, PhD candidate at the department of Methodology and Statistics and the Leiden Centre of Data Science (LCDS).

Serge Rombouts, Professor of Methods of Cognitive Neuroimaging