Bio-inspired computing: constituents and challenges

Nature has remedies for almost all problems. Though biological systems exhibits organised, complex and intelligent behaviour, they comprise of simple elements and governed by simple rules. Hence, mimicking such systems has been the attraction of researchers in the fields of computer science, neuroscience and biology for a long time. Generating complex behaviour from small agents working locally following simple rules is a highly cost-effective solution of the real life problem. Bio-inspired computing can be achieved through different models such as stochastic, ad hoc or discrete models; new paradigm inspired from nature like evolutionary approach and immune systems; and new platform, novel architecture and specially designed material such as artificial fuel cell. The consortium of bio-inspired computing are artificial neural networks, evolutionary algorithms, swarm intelligence, artificial immune systems, fractal geometry, artificial life, DNA computing and quantum computing, etc. This article discusses consortium of bio-inspired computing along with applications and research scope. In spite of having advantages offered by partial simulation of natural intelligence, there are some limitations of the bio-inspired computing that need to be addressed. These challenges include creation of new model, techniques and platforms for bio-inspired computing. This article concludes with the challenges to be explored in the field.

[1]  Nadine N. Tschichold-Gürman,et al.  Generation and improvement of fuzzy classifiers with incremental learning using fuzzy RuleNet , 1995, SAC '95.

[2]  Melanie Mitchell,et al.  An introduction to genetic algorithms , 1996 .

[3]  G. Vukovich,et al.  A fuzzy genetic algorithm with effective search and optimization , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[4]  L M Adleman,et al.  Molecular computation of solutions to combinatorial problems. , 1994, Science.

[5]  Victor A. Skormin,et al.  Immunocomputing - principles and applications , 2003 .

[6]  Leszek Rutkowski,et al.  Flexible neuro-fuzzy systems , 2003, IEEE Trans. Neural Networks.

[7]  Hiroaki Kitano,et al.  Empirical Studies on the Speed of Convergence of Neural Network Training Using Genetic Algorithms , 1990, AAAI.

[8]  Michael A. Craft,et al.  A Stigmergic Cooperative Multi-Robot Control Architecture , 2004 .

[9]  Alan S. Perelson,et al.  The immune system, adaptation, and machine learning , 1986 .

[10]  E. Bonabeau,et al.  Three-dimensional architectures grown by simple 'stigmergic' agents. , 2000, Bio Systems.

[11]  Vincenzo Cutello,et al.  An Immunological Approach to Combinatorial Optimization Problems , 2002, IBERAMIA.

[12]  Xin Yao,et al.  A new evolutionary system for evolving artificial neural networks , 1997, IEEE Trans. Neural Networks.

[13]  Rudolf Kruse,et al.  NEFCLASSmdash;a neuro-fuzzy approach for the classification of data , 1995, SAC '95.

[14]  J Timmis,et al.  An artificial immune system for data analysis. , 2000, Bio Systems.

[15]  Lotfi A. Zadeh.  Toward Human Level Machine Intelligence - Is It Achievable? The Need for a Paradigm Shift , 2008 .

[16]  Asli Celikyilmaz.  Modeling uncertainty with evolutionary improved fuzzy functions , 2008 .

[17]  D. Dasgupta.  Artificial Immune Systems and Their Applications , 1998, Springer Berlin Heidelberg.

[18]  Yuichi Nakamura,et al.  Approximation of dynamical systems by continuous time recurrent neural networks , 1993, Neural Networks.

[19]  Gheorghe Paun,et al.  Bio-inspired Computing Paradigms (Natural Computing) , 2004, UPP.

[20]  Steven H. Strogatz,et al.  Nonlinear Dynamics and Chaos , 2024 .

[21]  Matthew Cook,et al.  Universality in Elementary Cellular Automata , 2004, Complex Syst..

[22]  Jon Timmis,et al.  Jisys: The Envelopment of an Artificial Immune System for Real World Applications , 1999 .

[23]  Mitchell A. Potter,et al.  The design and analysis of a computational model of cooperative coevolution , 1997 .

[24]  Hugues Bersini,et al.  Hints for Adaptive Problem Solving Gleaned from Immune Networks , 1990, PPSN.

[25]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[26]  Byoung-Tak Zhang,et al.  Hypernetworks: A Molecular Evolutionary Architecture for Cognitive Learning and Memory , 2008, IEEE Computational Intelligence Magazine.

[27]  Udo Seiffert,et al.  Multiple Layer Perceptron training using genetic algorithms , 2001, ESANN.

[28]  Ajith Abraham,et al.  Neuro Fuzzy Systems: Sate-of-the-Art Modeling Techniques , 2001, IWANN.

[29]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[30]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[31]  Kagan Tumer,et al.  Collective Intelligence and Braess' Paradox , 2000, AAAI/IAAI.

[32]  Linda See,et al.  Applying soft computing approaches to river level forecasting , 1999 .

[33]  D. O. Hebb,et al.  The organization of behavior , 1988 .

[34]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[35]  G. Theraulaz,et al.  Inspiration for optimization from social insect behaviour , 2000, Nature.

[36]  Saman K. Halgamuge,et al.  Neural networks in designing fuzzy systems for real world applications , 1994 .

[37]  D. Dasgupta,et al.  Advances in artificial immune systems , 2006, IEEE Computational Intelligence Magazine.