Machine Learning Blog

Monthly Archives: October 2019

Psychology Seminar, 23 Oct, 1:00pm

News, Reading Group.

Department of Psychology seminar

When: Wed, 23 October 2019, 1:00pm
Where: D427, Rhind Building

Who: Bert Kappen; Donder Institute, Radboud University Nijmegen (Netherlands)

Title: Path Integral Control Theory

Abstract: Stochastic optimal control theory deals with the problem of computing an optimal set of actions to attain some future goal. Examples are found in many contexts such as motor control tasks for robotics, planning and scheduling tasks or managing a financial portfolio. The computation of the optimal control is typically very difficult due to the size of the state space and the stochastic nature of the problem. For a special class of non-linear stochastic control problems, the solution can be mapped onto a statistical inference problem. For these so-called path integral control problems the optimal cost-to-go solution of the Bellman equation is given by the minimum of a free energy. I will give a high level introduction to the underlying theory and illustrate with some examples from robotics and other areas.

Bio: Prof. Bert Kappen conducts theoretical research that lie at the interface between machine learning, control theory, statistical physics, computer science, computational biology and artifcial intelligence. He has developed many novel approximate inference methods inspired by methods from statistical physics. He has pioneered the mean field analysis of stochastic neural networks with dynamical synapses, revealing up and down states and rapid switching. He has identified a novel class of non-linear stochastic control problems that can be solved using path integrals. This approach has been adapted by leading robotics groups world wide, and is recognized as an important novel approach to stochastic control. His work on mean field theory for asymmetric stochastic neural networks is at the basis of current research to find connectivity patterns in neural circuits. He is author of about 130 peer reviewed articles in scientific journals and leading conferences. In collaboration with medical experts, he has developed a Bayesian medical expert system, including approximate inference methods, and he has co-founded the company Promedas to commercialize this system. He is director of SNN, the Dutch foundation for Neural Networks. SNN has a long reputation for successfully applying neural network and machine learning methods in collaboration with numerous industrial partners. He has co-founded the company Smart Research bv, that offers commercial service on machine learning and that has developed the Bonaparte Disaster Victim Identification software. He is honorary faculty at the Gatsby Unit for Computational Neuroscience at University College London. For more information:

All welcome!


MPhil-PhD transfer seminar – Benedikt Wagner

News, Seminar.

MPhil-PhD transfer presentation

When: Wed, 16th Oct 2019, 12.00 noon
Where: A108 (1st Floor, College Building)

Who: Benedikt Wagner; City, University of London

Title: Reasoning about what has been learned: Knowledge Extraction from Neural Networks

Abstract: Machine Learning-based systems, including Neural Networks, are experiencing greater popularity in recent years. A weakness of these model that rely on complex representations is that they are considered black boxes with respect to explanatory power. In the context of current initiatives on the side of the regulatory authorities and societal discussions regarding, a desire for transparency and corresponding accountability of automated decision systems, attempts on better interpretable or explainable methods and systems in Artificial Intelligence and Machine Learning is ongoing. As a result, there has been a plethora of methods introduced in recent years, resulting in a large mixture of approaches and steps towards getting a better understanding of the behaviour of a model. Therefore, we have developed a taxonomy that provides a holistic view and structure on the topic. We further investigate three promising methods deeper which are based on Counterfactuals, Concept Activation Vectors, and Knowledge Extraction approaches. Concept Activation Vectors try to target the hidden representation as useful base for explanations based on conceptual sensitivities. The tree-structured Knowledge Extraction methods, on the other hand, aim at global representation in a constrained architecture that illustrate how a decision was made and achieve reasonable predictive performance. We emphasise potential benefits and weaknesses of the methods before providing an outlook on promising directions for future research.

All welcome!

Find us

City, University of London

Northampton Square

London EC1V 0HB

United Kingdom

Back to top

City, University of London is an independent member institution of the University of London. Established by Royal Charter in 1836, the University of London consists of 18 independent member institutions with outstanding global reputations and several prestigious central academic bodies and activities.