Autonomous Design Of Modular Intelligent Systems

  title={Autonomous Design Of Modular Intelligent Systems},
  author={Pavel Nahodil and Jaroslav V{\'i}tků},
We propose our original system capable of autonomous design of general-purpose complex modular hybrid systems. The resulting hybrid systems will be able to employ various techniques of learning, decisionmaking, prediction etc. Presented topic is from Artificial Life domain, but contributes also to fields such as Artificial Intelligence, Biology, Computational Neuroscience, Ethology, Cybernetics and potentially into many other aspects of research. The autonomous design is implemented as an… 


New Hybrid Architecture in Artificial Life Simulation
It is shown how it is possible, with help of the AI bottom-up methods, ethological and evolution principles, to simulate agents who have needs and desires, reflexes and instincts, but also have ability to perform deliberative tasks and to accomplish more complex goals.
Hybrid Neural Systems
An overview of Hybrid Neural Systems and Lessons from Past, Current Issues, and Future Research Directions in Extracting the Knowledge Embedded in Artificial Neural Networks are presented.
A Review Of Methods For Encoding Neural Network Topologies In Evolutionary Computation
The target of this review is to cover the main techniques of network encoding and make it easier to choose one when implementing a custom evolutionary algorithm for finding the network topology.
On logic synthesis of conventionally hard to synthesize circuits using genetic programming
A method of minimization of multi-level logic networks which can solve these difficult circuit instances using a search algorithm called Cartesian genetic programming (CGP), which is able to implicitly discover new efficient circuit structures.
Modular Neural Networks A Survey
The different motivations for creating MNNs are surveyed: biological, psychological, hardware, and computational, and the general stages of MNN design are outlined and surveyed, viz., task decomposition techniques, learning schemes and multi-module decision-making strategies.
Heuristic Self-Organization in Problems of Engineering Cybernetics
The Group Method of Data Handling (GMDH) based on the principles of heuristic self-organization is developed to solve complex problems with large dimensionality when the data sequence is very short.
Neural Engineering: Computation, Representation, and Dynamics in Neurobiological Systems
The authors present three principles of neural engineering based on the representation of signals by neural ensembles, transformations of these representations through neuronal coupling weights, and the integration of control theory and neural dynamics, and argue that these guiding principles constitute a useful theory for generating large-scale models of neurobiological function.
Networks of spiking neurons: the third generation of neural network models
  • W. Maas
  • Biology, Computer Science
  • 1997
ROS: an open-source Robot Operating System
This paper discusses how ROS relates to existing robot software frameworks, and briefly overview some of the available application software which uses ROS.
Networks of Spiking Neurons: The Third Generation of Neural Network Models
  • W. Maass
  • Computer Science
    Electron. Colloquium Comput. Complex.
  • 1996