A Reversible-Logic based Architecture for Artificial Neural Network

High-performance computing beyond sub-10 nm advanced node technology allows us to explore and use complex 2.5D/3D SOC design architecture. Node scaling, heterogeneous integration, and complex design enable us to think beyond Moore’s law but, at the same time, limit the scope with concerns of excessive power dissipation. The field of quantum computation and reversible logic functions has been researched in recent years in the context of low power VLSI circuit designs and nanotechnology. Reversible computation exhibits significantly reduced power dissipation in digital circuits. In this paper, we propose a novel design of Artificial Neural Network (ANN) using reversible logic gates. A thorough search of the relevant literature yielded only a few related articles. To the best of our knowledge, our proposed approach is the first attempt to implement a complete feedforward neural network circuit using only reversible logic gates. The comparative analysis demonstrates that our proposed approach has achieved an approximately 16% reduction in overall power dissipation compared to existing approaches. The proposed approach also has better scalability than the classical design approach.

[1]  Magdy A. Bayoumi,et al.  An Efficient Approach for Neural Network Architecture , 2018, 2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS).

[2]  R. Muthaiah,et al.  Optimized low power full adder design , 2017, 2017 International Conference on Networks & Advances in Computational Technologies (NetACT).

[3]  Raghava Garipelly.  A Review on Reversible Logic Gates and their Implementation , 2013 .

[4]  Naohiro Ishii,et al.  Analog Neural Circuit and Hardware Design of Deep Learning Model , 2015, KES.

[5]  Sujata S. Chiwande.  Introduction to Reversible Logic Gates & its Application , 2011 .

[6]  G. Wang.  A unified unsigned/signed binary multiplier , 2004, Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, 2004..

[7]  Christophe Loyez,et al.  A 4-fJ/Spike Artificial Neuron in 65 nm CMOS Technology , 2017, Front. Neurosci..

[8]  K. Besbes,et al.  Digital hardware implementation of a neural network used for classification , 2004, Proceedings. The 16th International Conference on Microelectronics, 2004. ICM 2004..

[9]  Hafiz Md. Hasan Babu,et al.  Efficient Design of Shift Registers Using Reversible Logic , 2009, 2009 International Conference on Signal Processing Systems.

[10]  Magdy A. Bayoumi,et al.  A Novel Design Gate based Low-Cost Configurable RO PUF using Reversible Logic , 2019, 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS).

[11]  Magdy A. Bayoumi,et al.  A Novel Reconfigurable Hardware Architecture of Neural Network , 2019, 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS).

[12]  Anas N. Al-Rabadi,et al.  Reversible logic neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[13]  M. Surekha,et al.  Efficient Approaches for Designing Quantum Costs of Various Reversible Gates , 2017 .

[14]  Charles H. Bennett,et al.  Logical reversibility of computation , 1973 .

[15]  G.E. Moore,et al.  Cramming More Components Onto Integrated Circuits , 1998, Proceedings of the IEEE.

[16]  R. Landauer,et al.  Irreversibility and heat generation in the computing process , 1961, IBM J. Res. Dev..

[17]  Magdy Bayoumi,et al.  Machine Learning-Based Approach for Hardware Faults Prediction , 2020, IEEE Transactions on Circuits and Systems I: Regular Papers.

[18]  K. V. Ramanaiah,et al.  Hardware Implementation of Artificial Neural Networks , 2015 .

[19]  H.S. Abdel-Aty-Zohdy,et al.  Implementation of programmable digital sigmoid function circuit for neuro-computing , 1998, 1998 Midwest Symposium on Circuits and Systems (Cat. No. 98CB36268).

[20]  Kasem Khalil,et al.  Intelligent Fault-Prediction Assisted Self-Healing for Embryonic Hardware , 2020, IEEE Transactions on Biomedical Circuits and Systems.

[21]  Mats Forssell,et al.  Hardware Implementation of Artificial Neural Networks , 2015 .

[22]  Majid Ahmadi,et al.  Precise digital implementations of hyperbolic tanh and sigmoid function , 2016, 2016 50th Asilomar Conference on Signals, Systems and Computers.

[23]  Osvaldo Simeone,et al.  An Introduction to Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications. , 2018 .

[24]  Ying-Shieh Kung,et al.  Digital hardware implementation of a radial basis function neural network , 2016, Comput. Electr. Eng..