Neuromolecularware – A Bio-inspired Evolvable Hardware and Its Application to Medical Diagnosis
Computer systems have powerful computational capability. However, it is brittle in that a slight program modification can inadvertently change the system functions. Biological systems demonstrate better adaptability than computer systems. An evolvable neuromolecular hardware motivated from some biological evidence is proposed. The hardware was further applied to medical diagnosis with a clinical database of premature babies who are given total parental nutrition (TPN). Experimental results show that the neuromolecular hardware was capable of learning to differentiate data in an autonomous manner.
KeywordsAdaptability Artificial Brain Evolvable Hardware Evolutionary Learning Medical Diagnosis
Unable to display preview. Download preview PDF.
- 5.Gordon, T.W., Bentley, P.J.: Towards Development in Evolvable Hardware. In: Proc of the 2002 NASA/DoD Conference on Evolvable Hardware (2002)Google Scholar
- 7.Hameroff, S.R.: Ultimate Computing. North-Holland, Amsterdam (1987)Google Scholar
- 8.GriPth, L.M., Pollard, T.D.: The interaction of actin filaments with microtubules and microtubule-associated proteins. J. Biol. Chem. 257, 9143–9151 (1982)Google Scholar