Ideas
Partners
Consultants
Calls
EU Projects
Blog NEW
- Europe towards City Innovation Hubs
  
  Written by Matteo Satta EU funding has always helped cities support their innovation processes, particularly on digital transformation and environment, but the approach is now moving toward a new ambitious […]
- Mistakes that Cities Should Be Avoiding in EU Projects
  
  By Matteo Satta Nowadays, we are seeing an increasing trend of people requesting to lower taxes and, as a result, public budgets. This leads many cities to try to find […]
- How a city can boost your Smart City project
  
  By Matteo Satta The commission has been heavily investing in pilot Smart City projects for a long time, but you may often have R&D or innovation projects pretending to have […]
- How to involve a city in your project? Here are a few tips.
  
  Article written by Matteo Satta (Smart) City projects are more and more funded by the European Commission, but consortia often struggle to get cities on board or really engage them. […]
- >> See all posts
Log In Sign Up

Want to see this project on homepage?
Propose a Picture

Composing Learning for Artificial Cognitive Systems (CompLACS)
Start date: Mar 1, 2011, End date: Feb 28, 2015 PROJECT FINISHED

Description One of the aspirations of machine learning is to develop intelligent systems that can address a wide variety of control problems of many different types. Currently, the technology used to specify, solve and analyse one control problem typically cannot be reused on a different problem. The purpose of CompLACS is to develop a unified toolkit that will incorporate the most successful approaches to control problems within a single framework, including bandit problems, Markov Decision Processes (MDPs), Partially Observable MDPs (POMDPs), continuous stochastic control, and multi-agent systems. The toolkit will also provide a generic interface to specifying problems and analysing performance, by mapping intuitive, human-understandable goals into machine-understandable objectives, and by mapping algorithm performance and get back into human-understandable terms.