A novel MLP network implementation in CMOL technology

Abstract Hybrid CMOS/nanodevice technology is a well-known candidate to extend the exponential Moor-Law progress of microelectronics beyond the 10-nm frontier. This paper presents and evaluates a novel method for synaptic weights implementation of artificial neural networks in CMOL technology, a hybrid CMOS/nanodevice technology. In this novel method, the analog property of the I–V characteristic of the nanodevice is utilized to implement each neuromorphic synaptic weight. Each synaptic weight is also implemented by using one nanodevice instead of several nanodevices. Moreover, the proposed method is applied to the multilayer perceptron (MLP) network in CMOL technology. Our analysis shows that the power consumption and speed are effectively improved in the proposed method compared to other methods at the expense of a reasonable overhead defect tolerance.

[1]  Shukai Duan,et al.  Memristive crossbar array with applications in image processing , 2012, Science China Information Sciences.

[2]  Massimiliano Di Ventra,et al.  Practical Approach to Programmable Analog Circuits With Memristors , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[3]  Mojtaba Joodaki,et al.  Future Prospect of Nanoelectronic Devices , 2013 .

[4]  Mei Liu,et al.  Three-dimensional CMOL: three-dimensional integration of CMOS/nanomaterial hybrid digital circuits , 2007 .

[5]  Jung Hoon Lee,et al.  In Situ Training of CMOL CrossNets , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[6]  Luca Maria Gambardella,et al.  Deep Big Multilayer Perceptrons for Digit Recognition , 2012, Neural Networks: Tricks of the Trade.

[7]  Gholam-Ali Hossein-Zadeh,et al.  Estimation of direct nonlinear effective connectivity using information theory and multilayer perceptron , 2014, Journal of Neuroscience Methods.

[8]  Andreas Mayr,et al.  CrossNets: High‐Performance Neuromorphic Architectures for CMOL Circuits , 2003, Annals of the New York Academy of Sciences.

[9]  Ahmad Ayatollahi,et al.  STDP implementation using memristive nanodevice in CMOS-Nano neuromorphic networks , 2009, IEICE Electron. Express.

[10]  Sangjae Lee,et al.  Predicting the helpfulness of online reviews using multilayer perceptron neural networks , 2014, Expert Syst. Appl..

[11]  Scott Hauck,et al.  Reconfigurable Computing: The Theory and Practice of FPGA-Based Computation , 2007 .

[12]  Mahmoud Ahmadian,et al.  Design and evaluation of basic standard encryption algorithm modules using nanosized complementary metal–oxide–semiconductor–molecular circuits , 2006 .

[13]  O. Turel,et al.  Possible nanoelectronic implementation of neuromorphic networks , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[14]  S. Haddad,et al.  Non-volatile resistive switching for advanced memory applications , 2005, IEEE InternationalElectron Devices Meeting, 2005. IEDM Technical Digest..

[15]  Khaled N. Salama,et al.  Memristor-based memory: The sneak paths problem and solutions , 2013, Microelectron. J..

[16]  André DeHon,et al.  Seven strategies for tolerating highly defective fabrication , 2005, IEEE Design & Test of Computers.

[17]  Hao Yu,et al.  Analysis and Modeling of Internal State Variables for Dynamic Effects of Nonvolatile Memory Devices , 2012, IEEE Transactions on Circuits and Systems I: Regular Papers.

[18]  Dmitri B. Strukov,et al.  3D CMOS-memristor hybrid circuits: devices, integration, architecture, and applications , 2012, ISPD '12.

[19]  Anupriya Rajkumar,et al.  A Study on Paraphrase Recognition Using Radial Basis Function Neural Network , 2012 .

[20]  S. Folling,et al.  Single-electron latching switches as nanoscale synapses , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[21]  Özgür Türel,et al.  CrossNets: Neuromorphic Networks for Nanoelectronic Implementation , 2003, ICANN.

[22]  Nasser Masoumi,et al.  Design investigation of nanoelectronic circuits using crossbar-based nanoarchitectures , 2013, Microelectron. J..

[23]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[24]  R. Stanley Williams,et al.  CMOS-like logic in defective, nanoscale crossbars , 2004 .

[25]  Aboul Ella Hassanien,et al.  MRI breast cancer diagnosis hybrid approach using adaptive ant-based segmentation and multilayer perceptron neural networks classifier , 2014, Appl. Soft Comput..

[26]  Xiaolong Ma,et al.  Architectures for nanoelectronic implementation of artificial neural networks: new results , 2005, Neurocomputing.

[27]  R. Rosezin,et al.  High density 3D memory architecture based on the resistive switching effect , 2009 .

[28]  Kow-Ming Chang,et al.  The resistive switching characteristics of a Ti/Gd2O3/Pt RRAM device , 2010, Microelectron. Reliab..

[29]  Dmitri B. Strukov,et al.  Digital architectures for hybrid CMOS/nanodevice circuits , 2006 .

[30]  Konstantin K. Likharev,et al.  Electronics Below 10 nm , 2003 .

[31]  D. Strukov,et al.  CMOL: Devices, Circuits, and Architectures , 2006 .

[32]  Konstantin K. Likharev,et al.  Hybrid CMOS/Nanoelectronic Circuits: Opportunities and Challenges , 2008 .

[33]  Gregory S. Snider,et al.  A Defect-Tolerant Computer Architecture: Opportunities for Nanotechnology , 1998 .

[34]  R. Velo,et al.  Wind speed estimation using multilayer perceptron , 2014 .

[35]  Peng Li,et al.  Dynamical Properties and Design Analysis for Nonvolatile Memristor Memories , 2011, IEEE Transactions on Circuits and Systems I: Regular Papers.

[36]  Changjian Gao,et al.  Cortical Models Onto CMOL and CMOS— Architectures and Performance/Price , 2007, IEEE Transactions on Circuits and Systems I: Regular Papers.

[37]  Parviz Keshavarzi,et al.  A novel digital logic implementation approach on nanocrossbar arrays using memristor-based multiplexers , 2014, Microelectron. J..

[38]  Konstantin K. Likharev,et al.  CrossNets: Neuromorphic Hybrid CMOS/Nanoelectronic Networks , 2011 .

[39]  R. Williams,et al.  Nano/CMOS architectures using a field-programmable nanowire interconnect , 2007 .