Ecole - Experience based
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 766186. EU Flag

Experience-based COmputation: Learning to optimisE

Ecole

Learning to Optimise

ECOLE, is an Innovative Training Network (ITN) for early stage researchers (ESRs) coordinated by the University of Birmingham. It is based on novel synergies between nature inspired optimisation and machine learning. The training programme will be targeted at the automotive industry, but the skill set of the early-stage researchers (ESRs) will be equally valuable to other fast-moving, innovative industries. This four year programme will yield a new generation of high achieving, early stage researchers who will be provided with the transferable skills necessary for thriving careers in emerging and rapidly developing industrial areas.

ECOLE is the first project of its kind in terms of studying Learning to Optimise systematically. It aims explicitly to understand and characterise “experience” in engineering optimisation and apply such abstracted experience to optimise different, but related, engineering problems. It aims at solving a series of related optimisation problems, instead of treating each problem instance in isolation. In order to study these research issues synergistically, 8 different ESRs are employed to tackle different aspects of the whole research challenge. This report details the progresses made in the ECOLE project in its first year although the ESRs have been in place for only half a year (approximately) according to proposed plan.

Research aim

The research aims of ECOLE include shortening the product cycle, reducing the resource consumption during the complete process and creating more balanced and innovative products. Instead of just developing technologies to solve a given optimisation problem, it will take a bold step forward and propose to optimise automatically across problems. Referring to knowledge, skill, and practice derived from problem solving processes in time, the experience of optimising one product or process will be learned and transferred automatically to solve other optimisation problems.

ECOLE is the first project of its kind in terms of studying Learning to Optimise systematically. It aims explicitly to understand and characterise “experience” in engineering optimisation and apply such abstracted experience to optimise different, but related, engineering problems. It aims at solving a series of related optimisation problems, instead of treating each problem instance in isolation. In order to study these research issues synergistically, 8 different ESRs are employed to tackle different aspects of the whole research challenge.

Purpose

ECOLE is needed in response to an acute shortage of human experts with sufficient skills in tackling industrial challenges in a holistic manner. A holistic view and approach are needed as the engineering process has profoundly changed in the last ten years. Many tools from computer aided design, computer aided engineering, and enterprise resource management have been integrated into product lifecycle management frameworks used in the automotive industry with the aim to enable a holistic view on the production processes. This will allow for the early embedding of constraints and criteria that occur late in the development chain or even the complete lifecycle of the product.

Download the ECOLE Website About Page as a PDF

Summary of Seminars and Meetings for ESR Training

EventLead institutionPurpose
1-day seminarHRI-EUPractical applications of multi- and many objective design optimisation in automotive industry
1-day seminarHRI-EURepresentations for design optimisation of complex bodies in automotive industry
1-day seminarHRI-EUCurrent state of industrial meta-model supported design optimisation of vehicles
Summer school (SS2)NECKnowledge transfer on Bayesian Inference, Probabilistic Graphical Models, Gaussian Processes, Bayesian Latent Variables and Topic Models, Representation Learning and Deep Nets
1-day seminarHRI-EUData mining and knowledge extraction of industrial car body data
WorkshopNECTraining on machine learning techniques for complex data analysis such as unstructured text data, time series data, and network data
HRI-EGN Symposium (SS3)HRI-EUHRI-EGN event for broad scientific exchange (attended by all PhD studnts and selected Master/Diploma students supported by HRI-EU)
1-day seminarHRI-EUProduct lifecycle management in automotive industry in the light of Industry 4.0
Summary of Training Modules Provided by ECOLE
Nature Inspired Search and Optimisation: A comprehensive introduction to the field of natural inspired optimisation, covering theories, algorithms and applications.
Intelligent Data Analysis: A comprehensive introduction to statistical pattern analysis, high-dimensional data mining, and text mining.
Machine Learning: Advanced topics in machine learning, covering several forms of supervised, semi-supervised and unsupervised learning, in both theories and applications.
Multiple-Criteria Optimisation and Decision Analysis: Theoretical foundations, algorithms, and application techniques of multi-objective optimisation.
Advances in Data Mining: Recent developments in data mining for classification, regression and clustering and beyond, dealing with massive data sets. Techniques for distributed data mining (e.g., Hadoop).
Evolutionary Algorithms: State-of-the-art in evolutionary computation; including efficient optimisation techniques (i.e., small number of function evaluations).
Research Skills: Including literature review, academic writing, referencing, LATEX, presentations, etc.
Reading Groups: In reading group meetings, ESRs will discuss his/her work to the rest of the group on a rotating basis and strengthen their communication skills and confidence in presenting their work.
Research Seminars: In seminars, primarily given by external speakers, ESRs will network with leading professionals and extend their research insights.
Outreach training courses: Half-day course focusing on the effective communication of research to wider public and academic community.
Time management course: Half-day course discusses planning techniques and resources for time management, helping students to prioritise to-do lists.
Speed reading workshop: Half-day workshop aiming at improving personal skills for more effective handling of reading material, master the techniques of scanning and skimming and improve the retention of written documents.
Talent pool: A unique five-day programme for ESRs, providing customised professional development training and access to practical, ‘real-life’ opportunities to develop the next generation of academics, business consultants and entrepreneurs.
Enterprise training programme (Medici): A training programme with flexible time, helping ESRs realise the commercial potential of their research, covering business strategies, marketing, finance and business planning, funding opportunities, sale and negotiation skills and networking skills.
Open science programme: Focus on publishing and communicating scientific knowledge and in particular open access and open data strategies and techniques.
Intellectual Property Rights: One-hour introduction to the formal aspects of intellectual properties, including guidelines on how to summarize research results in a way that they can be turned into powerful IPR by IPR professionals.
Technology Evaluation and Transfer: One-hour introduction to the steps of turning research results into technology, technology into innovations and innovations into products and services with a sustainable business value.
Project Management in Research: Planning, Quality and Risks: One-hour introduction to different standard methods for project management, including risk management.