Treffer: Learning agent in heuristic architecture optimization

Title:
Learning agent in heuristic architecture optimization
Authors:
Abelló Gàllego, Clara
Contributors:
Heredia, F.-Javier (Francisco Javier), Dr. Daniel Selva, Cornell University. Sibley School of Mechanical and Aerospace Engineering
Source:
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname
Publisher Information:
Universitat Politècnica de Catalunya, 2015.
Publication Year:
2015
Subject Terms:
Classificació AMS::90 Operations research, Decision trees, Multi-agent systems, Àrees temàtiques de la UPC::Matemàtiques i estadística::Investigació operativa::Optimització, Operations research, Investigació operativa, Management science, Classificació AMS::90 Operations research, mathematical programming::90B Operations research and management science, mathematical programming::90B Operations research and management science, Learning and adaptive systems, 90 Operations research, mathematical programming::90B Operations research and management science [Classificació AMS], Heuristics, Administració--Models matemàtics, Systems architecture, Matemàtiques i estadística::Investigació operativa::Optimització [Àrees temàtiques de la UPC]
Document Type:
Dissertation Bachelor thesis
File Description:
application/pdf
Language:
English
Access URL:
https://hdl.handle.net/2099.1/25726
http://hdl.handle.net/2099.1/25726
Accession Number:
edsair.dedup.wf.002..a4b41e2d23705020b2d5b955442443b0
Database:
OpenAIRE

Weitere Informationen

One of the main problems of current system design and architecture tools is the communication between the tool and the user and vice-versa. This work describes an on-going effort to improve that communication by incorporating an interactive and transparent learning agent into a multi-agent tradespace exploration tool. This learning agent mines the current population of individuals, which we will name architectures, for driving features (combination of architectural variables) that appear to drive architectures towards a "good region'' or a "bad region'' of the tradespace, and shares that information with the user. This information is used to produce a surrogate model based on a decision tree. The information about driving features is also fed to an adaptive heuristic optimization agent. Information about driving features, surrogate models, and heuristics can help the user understand the results of the tool better and gain useful architectural insight.
Outgoing