de Garis, H. (1990). Building Artificial Nervous Systems Using Genetically Programmed Neural Network Modules. Machine Learning: Proceedings of the Seventh International Converence, 132--139.

@InProceedings{deGaris1990,                 
  author =       {de Garis, Hugo},             
  title =        {Building Artificial Nervous Systems Using
  Genetically Programmed Neural Network Modules},             
  booktitle =    {Machine Learning: Proceedings of the Seventh
  International Conference},             
  crossref =     {},                
  key =          {},             
  pages =        {132--139},             
  year =         {1990},             
  editor =       {},             
  volume =       {},             
  number =       {},             
  series =       {},             
  address =      {},             
  month =        {},             
  organization = {},             
  publisher =    {},                
  note =         {},             
  annote =       {}              
}               

Author of the summary: Joel A. Pettis, 2006

Cite this paper for:

• Behavioural Memory is the tendency of a behaviour which was evolved in an earlier phase to persist in a later phase. [3]
• GenNets are powerful enough to provide highly time dependent control. [2]
• By combining the actions of many GenNets, it seems likely that it will be possible to build artificial nervous systems or "nanobrains". [4]
• GenNets can be combined to form a functioning (simulated) artificial nervous system. [4]
• A Darwin Machine is a theoretical tool that is able to implement many different GenNets very quickly.
• With suitable Darwin Machines, one can imagine teams of Genetic Programmers undertaking large scale projects to build much more sophisticated nervous systems with many thousands of GenNets. [5]
• Limitations in the Genetic Programming approach include both intra GenNet and inter GenNet limitations. [6]
• Use Shaping to evolve the behaviour of GenNets in multiple steps rather than one big step [6]
• Make sure the output curve has a non zero slope during the last few cycles of GenNet to allow the possibility of changing the output during later cycles [6] Avoid multi-function GenNets [6]
• Keep the number of evolutionary cycles of GenNets small [6]
• Weight your fitness measure of GenNets[6]
• Chaos is not a problem in GenNets since low fitness scores can be quickly eliminated [6]
• With nanotechnology, billions of nanorobots could function in parallel in a molecular environment, and report back to some central molecular processor, which determines the next generation. [6]

Genetic Programming uses the Genetic Algorithm (GA) to design neural network modules [de GARIS 1990]. The programmer specifies all of the characteristics and input parameters and the GA is used to find both the signs and the values of the weights of the network which provides the functionality desired. Once the weights are found, it is deemed a GenNet module and thus can be used as a component in a more complex structure.

GenNets are powerful enough to provide highly time dependent control [2]. This is shown using a simple pair of stick legs which are taught to walk :

• The aim of the exercise is to evolve GenNets which make the stick legs move as far as possible to the right in the user specified number of cycles and cycle time.
• The chromosomes used to evolve the weights and their signs in the GA are simple binary strings. With P binary places and N neurons, a chromosome will be N*N(P + 1) bits long
• Knowing the values of the angular accelerations and knowing the values of the angles and the angular velocities at the beginning of the cycle, one can calculate the values of the angles and angular velocities at the end of the cycle
• The quality of the criterion is the velocity of the stick legs moving to the right where right distances are non negative
• A series of experiments were performed

In the first experiment, no constraint was imposed on the motion of the stick legs. The resulting motion was un-lifelike but the legs still managed to learn to move to the right.

In the second experiment, the hip joint was restricted to remain above the floor. The evolution was slower and almost as un-lifelike as the first experiment.

In the third experiment, a full set of constraints were imposed to ensure a lifelike walking motion. The result was that the legs tried to take the longest steps possible and in turn "did the splits" which ceased the evolution. This was a valuable lesson on the important concept steps. The quality measure was the product of the number of net positive steps taken to the right and the distance