Structure Adaptation in Arti cial

There is a growing evidence that the human brain follows an environmentally-guided neural circuit building that increases its learning exibility. Similarly, it has been shown that artiicial neural networks with dynamic topologies attempt to overcome the problem of determining the appropriate topology to optimally solve a given application. This paper presents a modular structure-adaptable artiicial neural network architecture for autonomous control systems consisting of an unsuper-vised learning network, a reinforcement learning module and a planning module. Finally, we present an extension of the state representation of the environment by introducing short-term memories to deal with the problem of partial observability in the real-world.