| Revision as of 22:22, 3 February 2004 editChopchopwhitey (talk | contribs)518 edits altered recommended readings← Previous edit | Revision as of 23:34, 3 February 2004 edit undoChopchopwhitey (talk | contribs)518 editsmNo edit summaryNext edit → | ||
| Line 19: | Line 19: | ||
| *: non-technical overview of several of the topics involved in bio-inspired computing. | *: non-technical overview of several of the topics involved in bio-inspired computing. | ||
| * ''Emergence'', Steven Johnson. | * ''Emergence: The Connected Lives of Ants, Brains, Cities and Software'', Steven Johnson. | ||
| * ''Turtles, Termites and Traffic Jams'', Mitchel Resnick. | * ''Turtles, Termites and Traffic Jams'', Mitchel Resnick. | ||
| * ''Understanding Nonlinear Dynamics'', Daniel Kaplan and Leon Glass. | * ''Understanding Nonlinear Dynamics'', Daniel Kaplan and Leon Glass. | ||
Revision as of 23:34, 3 February 2004
Biologically-inspired computing (also bio-inspired computing) is a field of study that loosely knits together subfields related to the topics of connectionism, social behaviour and emergence. It is often closely related to the field of artificial intelligence, as many of its pursuits can be linked to machine learning. It relies heavily on the fields of biology, computer science and mathematics. Briefly put, it is the use of computers to model nature, and simultaneously the study of nature to improve the usage of computers.
Some areas of study encompassed under the canon of biologically-inspired computing, and their biological inspirations:
- genetic algorithms ↔ evolution
- cellular automata ↔ life
- emergent systems ↔ ants, termites, bees, etc
- neural networks ↔ the brain
- artificial life ↔ life
- lindenmayer systems ↔ plant structures
One way in which bio-inspired computing differs from AI is in how it takes a more evolutionary approach to learning, as opposed to the what could be described as 'creationist' methods used in traditional AI. In traditional AI, intelligence is often programmed from above: the programmer is the creator, and makes something and imbues it with its intelligence. Bio-inspired computing, on the other hand, takes a more bottom-up approach; bio-inspired techniques often involve the method of specifying a set of simple rules, a set of simple organisms which adhere to those rules, and a method of iteratively applying those rules. After several generations of rule application it is usually the case that some forms of complex behaviour arise. Complexity gets built upon complexity until the end result is something markedly complex, and quite often completely counterintuitive from what the original rules would be expected to produce (see complex systems).
Natural evolution is a good analogy to this method–the rules of evolution (selection, recombination/reproduction, and mutation) are in principle simple rules, yet over thousands of years have produced remarkably complex organisms. A similar technique is used in genetic algorithms.
Recommended readings
(the following are presented in ascending order of complexity and depth, with those new to the field suggested to start from the top)
- Get A-Life: non-technical overview of several of the topics involved in bio-inspired computing.
- Emergence: The Connected Lives of Ants, Brains, Cities and Software, Steven Johnson.
- Turtles, Termites and Traffic Jams, Mitchel Resnick.
- Understanding Nonlinear Dynamics, Daniel Kaplan and Leon Glass.
- The Computational Beauty of Nature, Gary William Flake. MIT Press, 1998 (An in-depth discussion of many of the topics and underlying themes of bio-inspired computing.)