##
**CrossNets: Possible neuromorphic networks based on nanoscale components.**
*(English)*
Zbl 1016.94045

Summary: Extremely dense neuromorphic networks may be based on hybrid 2D arrays of nanoscale components, including molecular latching switches working as adaptive synapses, nanowires as axons and dendrites, and nano-CMOS circuits serving as neural cell bodies. Possible architectures include ‘free-growing’ networks, which may form topologies very close to those of the cerebral cortex, and several species of distributed crossbar-type networks, ‘CrossNets’ (including notably ‘InBar’ and ‘RandBar’), with better density and speed scaling. Numerical modelling shows that the specific signal sign asymmetry used in CrossNets allows self-excitation of recurrent networks with long-range cell interaction, without a symmetry-breaking global latchup. Our next goal is to develop methods of globally supervised teaching of extremely large networks with no external access to individual synapses. Such development would open a way towards cerebral-cortex-scale networks (with \(\sim 10^{10}\) neural cells and \(\sim 10^{14}\) synapses) capable of advanced information processing and self-evolution at a speed several orders of magnitude higher than their biological prototypes.

### MSC:

94C05 | Analytic circuit theory |

68T05 | Learning and adaptive systems in artificial intelligence |

68M07 | Mathematical problems of computer architecture |

92B20 | Neural networks for/in biological studies, artificial life and related topics |

### Keywords:

single-electron devices; nanowires; nanoFETs; hybrid circuits; neuromorphic networks; synapses; crossbar arrays self-evolution; adaptation### Software:

CrossNets
PDF
BibTeX
XML
Cite

\textit{Ö. Türel} and \textit{K. Likharev}, Int. J. Circuit Theory Appl. 31, No. 1, 37--53 (2003; Zbl 1016.94045)

Full Text:
DOI

### References:

[1] | Fölling, Proceedings of the International Joint Conference on Neural Networks pp 216– (2001) |

[2] | Likharev, Single-electron devices and their applications, Proceedings of IEEE 87 (4) pp 606– (1999) |

[3] | 2001 http: //public.itrs.net/Files/2001ITRS/Home.htm |

[4] | Likharev, Advanced Semiconductor and Organic Nanotechnologies, Part 1 (2002) |

[5] | Amit, Modeling Brain Function (1989) |

[6] | Hertz, Introduction to the Theory of Neural Computation (1991) · JFM 25.0904.01 |

[7] | Fausett, Fundamentals of Neural Networks (1994) |

[8] | Hassoun, Fundamentals of Artificial Neural Networks (1995) |

[9] | Haykin, Neural Networks (1999) · Zbl 0934.68076 |

[10] | Sarle WS ftp.sas.com/pub/neural/FAQ.html.zip 2002 |

[11] | Churchland, The Computational Brain (1992) |

[12] | Mountcastle, Perceptual Neuroscience. The Cerebral Cortex. (1998) |

[13] | Braitenberg, Cortex: Statistics and Geometry of Neuronal Connectivity (1998) |

[14] | Albert, Statistical mechanics of complex networks, Review of Modern Physics 74 (1) pp 47– (2002) · Zbl 1205.82086 |

[15] | Akazawa, Boltzmann machine neuron circuit using single-electron tunneling, Applied Physics Letters 70 (5) pp 670– (1997) |

[16] | Averin, Macroscopic quantum tunneling of the electric charge in small tunnel junctions, Physics Letters A 140 (5) pp 251– (1989) |

[17] | njal.physics.sunysb.edu |

[18] | Yeomans, Statistical Mechanics of Phase Transitions (1992) |

[19] | Zankovych, Nanoimprint lithography: challenges and prospects, Nanotechnology 12 (2) pp 91– (2001) |

[20] | Grossberg, Nonlinear neural networks: Principles, mechanisms, and architectures, Neural Networks 1 (1) pp 17– (1988) |

This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.