Probabilistic Neural Network with Memristive Crossbar Circuits

The scalability and non-ideality issues of the memristor circuits poses several challenges to the implementation of analog memristive probabilistic neural networks in hardware. To meet the emerging challenges of faster edge AI computing devices, the integration of neural networks within or near to the sensor can improve the data processing times, reduce bandwidth requirements, and reduce data transfer errors. The fast learning in probabilistic neural network (PNN) make it an attractive solution for energy efficient computing in edge devices. The PNN estimates the density function of the categories and classifies the input based on the Bayes decision rule. It avoids backpropagation, since weights are derived from training samples directly and set in the first initialization stage. The proposed hardware realization of the PNN is based on a memristor crosssbar architecture. The simulations demonstrate that the accuracy of the hardware realization of the PNN can be as high as 93.3% for the MNIST dataset if a proper smoothing parameter is selected.

[1]  D. F. Specht,et al.  Enhancements to probabilistic neural networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[2]  Hongyi Li,et al.  An Incremental Learning Method Based on Probabilistic Neural Networks and Adjustable Fuzzy Clustering for Human Activity Recognition by Using Wearable Sensors , 2012, IEEE Transactions on Information Technology in Biomedicine.

[3]  R. Jacob.  High Speed Op-amp Design : Compensation and Topologies for Two and Three Stage Designs , 2007 .

[4]  T. Tsuji,et al.  FPGA Implementation of a Probabilistic Neural Network Using Delta-Sigma Modulation for Pattern Discrimination of EMG Signals , 2007, 2007 IEEE/ICME International Conference on Complex Medical Engineering.

[5]  Moritoshi Yasunaga,et al.  Reconfigurable architecture for probabilistic neural network system , 2003, Proceedings. 2003 IEEE International Conference on Field-Programmable Technology (FPT) (IEEE Cat. No.03EX798).

[6]  Yaowu Chen,et al.  FPGA Implementation of a Probabilistic Neural Network for Spike Sorting , 2010, 2010 2nd International Conference on Information Engineering and Computer Science.

[7]  M. Kumngern,et al.  Simple CMOS current-mode exponential function generator circuit , 2008, 2008 5th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[8]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[9]  Carlos Aristoteles De La Cruz Blas,et al.  Novel Low-Power High-dB Range CMOS Pseudo-Exponential Cells , 2006 .

[10]  Pietro Burrascano,et al.  Learning vector quantization for the probabilistic neural network , 1991, IEEE Trans. Neural Networks.

[11]  Spyros Stathopoulos,et al.  A Data-Driven Verilog-A ReRAM Model , 2018, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[12]  Cosmin Popa.  Pseudo-exponential computational circuit with improved accuracy and frequency response , 2012, 2012 Proceedings of the 35th International Convention MIPRO.

[13]  Kaushik Roy,et al.  M2CA: Modular Memristive Crossbar Arrays , 2018, 2018 IEEE International Symposium on Circuits and Systems (ISCAS).

[14]  Chris Yakopcic,et al.  Hybrid crossbar architecture for a memristor based cache , 2013, Microelectron. J..

[15]  Kandarpa Kumar Sarma,et al.  Phoneme-Based Speech Segmentation using Hybrid Soft Computing Framework , 2014 .

[16]  Jia Jia,et al.  Probabilistic neural network based motor cortical decoding method and hardware implementation , 2010, 2010 IEEE International Symposium on Computer-Aided Control System Design.

[17]  D. F. Specht,et al.  Experience with adaptive probabilistic neural networks and adaptive general regression neural networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[18]  Dong Wang,et al.  FPGA implementation of hardware processing modules as coprocessors in brain-machine interfaces , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[19]  Amanpreet Kaur,et al.  Current Mode Computational Circuits forAnalog Signal Processing , 2014 .