Neuromorphic Computing

  • Ultra-Low Energy Brain-Inspired Computing using Nanoscale Emerging Spintronic Devices
  • 3D nanotubular metal-insulator-metal memristors for neuro-inspired artificial intelligence
  • Self-Sustained Spin-Transfer Torque Devices based Brain-inspired Processor Powered by Energy Harvesting Technology for Internet of Things Applications

Human brains are vastly more energy efficient at interpreting the world visually or understanding speech than any CMOS based computer system of the same size. Neuromorphic computing can perform human-like cognitive computing, such as vision, classification, and inference. The fundamental computing units of artificial neural network are the neurons that connect to each other and external stimuli through programmable connections called synapses. The basic operation of an artificial neuron is summing the N weighted inputs and passing the result through a transfer (activation) function. Such neuron and synapse functions can be efficiently implemented using different emerging post-CMOS device technologies. Our research in this area include:

  • Physical modeling of nanoscale emerging devices for potential neuron or synapse applications, such as resistive RAM, spin-transfer torque devices, spin-orbit torque devices, magnetic domain wall motion devices, magnetic skyrmion, etc.
  • Exploration of various neuromorphic computing models, such as Deep Learning Convolutional Neural Network, Spiking Neural Network, Hierarchical Temporal Memory, Oscillatory Neural Network, etc
  • Cross-layer (device/ circuit/ architecture) co-design for implementing complex machine learning tasks, such as pattern/ speech recognition, semantic reasoning, robotic control and motion detection

Related Journal publications :

  1. [TMAG’22]  William Hwang, Fen Xue, Fan Zhang, Mingyuan Song, Chien-Min Lee, Emrah Turgut, T. C. Chen, Xinyu Bao, Wilman Tsai, Deliang Fan, Shan X. Wang, “Energy Efficient Computing with High-Density, Field-Free STT-Assisted SOT-MRAM (SAS-MRAM),”  IEEE Transactions on Magnetics (TMAG) , 2022, DOI: 10.1109/TMAG.2022.3224729 [pdf]
  2. [EDL’20] Durjoy Dev, Adithi Krishnaprasad, Mashiyat S. Shawkat, Zhezhi He, Sonali Das, Deliang Fan, Hee-Suk Chung, Yeonwoong Jung, and Tania Roy, “2D MoS2 Based Threshold Switching Memristor For Artificial Neuron,” IEEE Electron Device Letters (EDL), April 16, 2020 [pdf]
  3. [IEEE-DT’21]  Sai Kiran Cherupally, Jian Meng, Adnan Rakin, Shihui Yin, Mingoo Seok, Deliang Fan and Jae-sun Seo, “Improving DNN Hardware Accuracy by In-Memory Computing Noise Injection,” IEEE Design & Test of Computers , 2021 (conditional accept)
  4. [TCAS-II’21]  Jian Meng, Li Yang, Xiaochen Peng, Shimeng Yu, Deliang Fan and Jae-Sun Seo, “Structured Pruning of RRAM Crossbars for Efficient In-Memory Computing Acceleration of Deep Neural Networks,” IEEE Transactions on Circuits and Systems- II (TCAS-II) Vol. 68, No. 5, May 2021 [pdf]
  5. [TCAD’19] Baogang Zhang, Necati Uysal, Deliang Fan, Rickard Ewetz, “Handling Stuck-at-fault Defects using Matrix Transformation for Robust Inference of DNNs,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 30 September 2019, DOI: 10.1109/TCAD.2019.2944582  [pdf]
  6. [TMSCS’17] Y. Bai, D. Fan and M. Lin, “Stochastic-Based Synapse and Soft-Limiting Neuron with Spintronic Devices for Low Power and Robust Artificial Neural Networks,” IEEE Transactions on Transactions on Multi-Scale Computing Systems, vol.4, no.3, pp.463-476, Dec. 2017 [pdf]
  7. [MAGL’17] Z. He, S. Angizi, and D. Fan, “Current Induced Dynamics of Multiple Skyrmions with Domain Wall Pair and Skyrmion-based Majority gate Design,” IEEE Magnetics Letters, vol.8, March 30, 2017 [pdf]
  8. [JETC’17] K. Yogendra, C. Liyanagedera, D. Fan, Y. Shim and K. Roy, “Coupled Spin-Torque Nano-Oscillator based Computation: A Simulation Study,” ACM Journal on Emerging Technologies in Computing Systems, vol. 13, no.4, July 2017 [pdf]
  9. [TCAD’16] X. Fong, Y. Kim, K. Yogendra, D. Fan, A. Sengupta, and K. Roy, “Spin-Transfer Torque Devices: Prospects and Perspectives,” IEEE Transactions on Computer Aided Design of Integrated Circuits and Systems (TCAD), Vol. 25, no. 1, pp.1-22, Jan 2016, [pdf]
  10. [TED’16] K Yogendra, D. Fan, B. Jung and K. Roy, “Magnetic Pattern Recognition using Injection Locked Spin Torque Nano-Oscillators”, IEEE Transactions on Electron Devices, vol. 63, no. 4, pp.1674-1680, Feb. 2016 [pdf]
  11. [TNANO’15] D. Fan, S. Maji, K. Yogendra, M. Sharad and K. Roy, “Injection Locked, Spin Hall Induced Coupled-Oscillators for Energy Efficient Associative Computing,” IEEE Transaction on Nanotechnology (TNANO), Vol. 14, No. 6, Aug, 2015. DOI: 10.1109/TNANO.2015.2471092 [pdf]
  12. [TNNLS’15] D. Fan, M. Sharad, A. Sengupta and K. Roy, “Hierarchical Temporal Memory Based on Spin-Neurons and Resistive Memory for Energy-Efficient Brain-Inspired Computing,” IEEE Transaction on Neural Networks and Learning Systems (TNNLS), Vol.27, no.9, Sept. 2016. DOI: 10.1109/TNNLS.2015.2462731 [pdf]
  13. [TNANO’15] D. Fan, Y. Shim, A. Raghunathan and K. Roy, “STT-SNN: A Spin-Transfer-Torque Based Non-Linear Soft-Limiting Neuron for Low-Power Artificial Neural Networks,” IEEE Transactions on Nanotechnology (TNANO), June 2015. DOI: 10.1109/TNANO.2015.2437902 [pdf]
  14. [TMAG’15] K Yogendra, D. Fan and K. Roy, “Coupled Spin Torque Nano Oscillators for Low Power Neural Computation”, IEEE Transactions on Magnetics, Vol. 51, no. 10, June, 2015. DOI: 10.1109/TMAG.2015.2443042 [pdf]
  15. [TMAG’15] M. Sharad, D. Fan and K. Roy, “Energy-Efficient and Robust Associative Computing with Injection-Locked Dual Pillar Spin-Torque Oscillators”, IEEE Transactions on Magnetics, Vol. 51, No. 7, June 2015. DOI: 10.1109/TMAG.2015.2394379 [pdf]
  16. [JETCAS’15] K. Roy, D. Fan, X. Fong, Y. Kim, M. Sharad, S. Paul, S. Chatterjee, S. Bhunia, and S. Mukhopadhyay “Exploring Spin Transfer Torque Devices for Unconventional Computing”, IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS), Vol. 5, No. 1, March 2015. DOI: 10.1109/JETCAS.2015.2405171 [pdf]
  17. [TNANO’14] M. Sharad, D. Fan, and K. Roy, “Energy Efficient Non-Boolean Computing With Spin Neurons and Resistive Memory”, IEEE Transaction on Nanotechnology (TNANO), vol. 13, No.1, 2014. DOI: 10.1109/TNANO.2013.2286424 [pdf]
  18. [JAP’13] M. Sharad, D. Fan and K. Roy , “Spin Neurons: A Possible Path to Energy-Efficient Neuromorphic Computers”, Journal of Applied Physics (JAP), 114, 234906 (2013) http://dx.doi.org/10.1063/1.4838096 [pdf]
  19. Zhezhi He, Deliang Fan, “Developing All-Skyrmion Spiking Neural Network” arXiv:1705.02995, May 2017

Related Conference publications :

  1. [ASPDAC’22]  Fan Zhang, Li Yang, Jian Meng, Yu Cao, Jae-sun Seo, and Deliang Fan, “XBM: A Crossbar Column-wise Binary Mask Learning Method for Efficient Multiple Task Adaption,”  27th Asia and South Pacific Design Automation Conference (ASPDAC), Jan. 17-20, 2022 (accept)
  2. [DAC’21] Sai Kiran Cherupally, Adnan Rakin, Shihui Yin, Mingoo Seok, Deliang Fan and Jae-sun Seo. “Leveraging Variability and Aggressive Quantization of In-Memory Computing for Robustness Improvement of Deep Neural Network Hardware Against Adversarial Input and Weight Attacks”. In: 58th Design Automation Conference (DAC), San Francisco, CA, Dec. 5-9, 2021
  3. [IRPS’21] Wangxi He, Wonbo Shim, Shihui Yin, Xiaoyu Sun, Deliang Fan, Shimeng Yu, Jae-sun Seo, “Characterization and Mitigation of Relaxation Effects on Multi-level RRAM based In-Memory Computing,” IEEE International Reliability Physics Symposium, (IRPS), March 21-25, 2021 ( –Best Student Paper Candidate–) [pdf]
  4. [ASPDAC’20] Baogang Zhang, Necati Uysal, Deliang Fan, Rickard Ewetz, “Representable Matrices: Enabling High Accuracy Analog Computation for Inference of DNNs using Memristors,” Asia and South Pacific Design Automation Conference (ASP-DAC), Jan. 13-16, 2020, Beijing, China
  5. [DRC’19] Durjoy Dev, Adithi Krishnaprasad, Zhezhi He, Sonali Das, Mashiyat Sumaiya Shawkat, Madison Manley, Olaleye Aina, Deliang Fan, Yeonwoong Jung and Tania Roy, “Artificial Neuron using Ag/2D-MoS2/Au Threshold Switching Memristor,” 77th Device Research Conference, 23 – 26 June 2019, University of Michigan, Ann Arbor
  6. [DAC’19] Zhezhi He, Jie Lin, Rickard Ewetz, Jiann-Shiun Yuan and Deliang Fan, “Noise Injection Adaption: End-to-End ReRAM Crossbar Non-ideal Effect Adaption for Neural Network Mapping,” Design Automation Conference (DAC), June 2-6, 2019, Las Vegas, NV, USA [pdf] [code in GitHub]
  7. [GLSVLSI’18] Shaahin Angizi, Zhezhi He, Yu Bai, Jie Han, Mingjie Lin and Deliang Fan, “Leveraging Spintronic Devices for Efficient Approximate Logic and Stochastic Neural Network,” ACM Great Lakes Symposium on VLSI (GLSVLSI), Chicago, IL, USA, May 23-25, 2018 (invited) [pdf]
  8. [DATE’17]Z. He, D. Fan, “A Tunable Magnetic Skyrmion Neuron Cluster for Energy Efficient Artificial Neural Network,” Design, Automation and Test in Europe (DATE), Lausanne, Switzerland, 27-31 March, 2017 [pdf]
  9. [IJCNN’16]C. Liyanagedera, K. Yogendra, K. Roy and D. Fan, “ Spin Torque Nano-Oscillator based Oscillatory Neural Network”, 2016 IEEE International Joint Conference on Neural Network (IJCNN), Vancouver, Canada, July 24-29, 2016[pdf]
  10. [ASPDAC’16]K. Yogendra, D. Fan, Y. Shim, M. Koo, and K. Roy, “ Computing with Coupled Spin Torque Nano Oscillators”, 21st Asia and South Pacific Design Automation Conference (ASP-DAC), Macao, China, Jan. 25-28, 2016[pdf]
  11. [ASPDAC’16]A. Sengupta, K. Yogendra, D. Fan and K. Roy, “Prospects of efficient neural computing with arrays of magneto-metallic neurons and synapses”, 21st Asia and South Pacific Design Automation Conference (ASP-DAC), Macao, China, Jan. 25-28, 2016[pdf]
  12. [DATE’14]K. Roy, M. Sharad, D. Fan and K. Yogendra, “Brain-inspired computing with spin torque devices”, Design, Automation & Test in Europe (DATE), 2014. (invited tutorial)[pdf]
  13. [ISVLSI’14]K. Roy, M. Sharad, D. Fan and K. Yogendra, “Computing with Spin-Transfer-Torque Devices: Prospects and Perspectives,” IEEE Computer Society Annual Symposium on VLSI (ISVLSI), Tampa, FL, July 9-11, 2014 (special session paper)[pdf]
  14. [DAC’13]M. Sharad, D. Fan, and K. Roy, “Ultra Low Power Associative Computing With Spin Neurons and Resistive Crossbar Memory,” IEEE/ACM Design Automation Conference (DAC), Austin, TX, June 2-6, 2013[pdf]
  15. [ISLPED’13]K. Roy, M. Sharad, D. Fan, and K. Yogendra, “Beyond Charge-Base Computing: Boolean and Non Boolean computing Using spin Devices,” International Symposium on Low Power and Design (ISLPED), 2013. (invited tutorial)[pdf]
  16. [ICCAD’13]K. Roy, M. Sharad, D. Fan, and K. Yogendra, “Exploring Boolean and Non Boolean Computing Using Spin torque Switches” International Conference on Computer-Aided Design (ICCAD), 2013. (invited tutorial)[pdf]
  17. [ISQED’13]M. Sharad, D. Fan, and K. Roy, “Low Power and Compact Mixed-Mode Signal Processing Hardware using Spin-Neurons,” IEEE International Symposium on Quality Electronic Design (ISQED), Santa Clara, CA, March 4-6, 2013[pdf]
  18. [E3S’13]M. Sharad, D. Fan, K. Yogendra, and K. Roy, “Ultra-Low Power Neuromorphic Computing with Spin-Torque Devices,” 3rd Berkeley Symposium on Energy Efficient Electronic Systems, 2013[pdf]