Evolving Architecture – Dynamic and Intelligent Evolution of Artificial Agents in Complex Environments

Evolving Architecture – Dynamic and Intelligent Evolution of Artificial Agents in Complex Environments

Studio: FLOW 2018/2019

Project: Evolving Architecture – Adaptation of Artificial Neural Networks in Complex Dynamic Environments

Author: Karolína Kotnour, Ing. arch.

Supervisor: Miloš Florian, doc. Ing. arch. PhD.

Cooperation: Institute for Research in Science and Art, Robert B. Lisek,  MFA M.Phil. Ph.D.

Supported from Student Grant Competition: SGS19/117/OHK1/2T/15

The problem of the multi-agent environment of adaptive models brings up a number of the questions of the level of detail of each agent layer participating in the model. There has to be a reference grid to receive any relevant and comparable data in any case. For our scenario is vital to work with the spectro-temporal as well as Spatio-temporal characteristics.

Using the evolutionary algorithms we will be able to generate the correlated data from sensors and dynamic sound signals and to train the neural networks to stabilize these correlations in spatially represented relations.

The framework for representations in architecture and urban planning, in many contemporary contexts that can be characterized by the concept of ‘network’ and ‘flow’ created by adapting agents in dynamically evolving environments. The meta-learning framework can be used for analyzing, modulate and predict different complex systems e.g.: digital cities, information and communication networks.