Jyväskylä, Finland

Sequential Experimentation and decision making by Anytime Randomized Search Heuristics

when 15 August 2016 - 19 August 2016
language English
duration 1 week
credits 2 EC

This course on sequential experimentation will collect together work from a number of areas of modern science and engineering (from quantum control to synthetic biology), and show how they are converging on an automated approach to optimization and discovery. Complementary to the statistical or mathematical modeling mode usually employed in science, sequential experimentation (that is, experimenting with real processes and systems) allows us to achieve our scientific and technological goals efficiently and without reliable prior knowledge. The use or randomized search heuristics (such as evolutionary algorithms) is central to this emerging approach; this course will give students the knowledge of both the core algorithms and the practical challenges in this fast-moving area of applied optimization.
The course would have the following content:

• Optimization Concepts, Sequential Decision Making, and Search Heuristics
• Design of Experiments (Traditional and Modern Methods)
• Multiobjective Optimization and Constraint Handling
• Noise-Tolerance and Robustness
• Expensive Optimization Problems and Surrogate Modeling
• Applications of Sequential Experimentation and Decision-Making:
o Quantum control
o Hyperparameter optimization in machine learning
o MUSCLE - mass spectrometry experimentation
o Wind tunnel experiments in Formula 1 (to be confirmed)
o Food science and taste-testing
o Drug design and high-throughput assays
o Synthetic Biology
o The Future of Sequential Experimentation

Course leader

Lecturer: Prof. Joshua Knowles (University of Birmingham, United Kingdom)

Course coordinator: Dr. Karthik Sindhya (University of Jyvaskyla)

Target group

The course will build on basic concepts in probability, statistics, and discrete mathematics. It would be suitable for anyone with a numerate background who has an interest in learning about optimization and/or machine learning. No programming pre-requisite or other specialized knowledge is required.

The Summer School annually offers courses for advanced master’s students, graduate students, and post-docs in the various fields of science and information technology.

Course aim

The most important aims of the Summer School are to develop post-graduates scientific readiness and to offer students the possibility to study in a modern, scientific environment and to create connections to the international science community. The Summer School offers an excellent pathway to develop international collaboration in post-graduate research.

Credits info

2 EC
Passing: Obligatory attendance at lectures. The course will comprise lectures, and a small-group presentation summarizing a selected paper in sequential experimentation and decision making.

Grading: Pass/fail

Fee info

EUR 0: Participating the Summer School is free of charge, but student have to cover the costs of own travel, accommodation and meals at Jyväskylä.


The 26th Jyväskylä Summer School is not able to grant any Summer School students financial support.