臺灣博碩士論文加值系統

目錄
中文摘要 I
英文摘要 III
致謝 V
目錄 VI
圖目錄 VIII
表目錄 XII
第一章 緒論 1
1-1 前言 1
1-2 研究動機目的 1
1-3 論文架構說明 2
第二章 文獻回顧與基礎理論 4
2-1 非馮紐曼架構(Non Von Neumann Architecture) 4
2-2 神經系統構造和記憶模型 5
2-3 類神經網路(Artificial Neural Network) 8
2-4 電阻式記憶體介紹 12
2-5 硬體神經網路(Hardware Neural Network，HNN) 17
2-6電阻式記憶體之突觸元件裝置探討 20
2-7電子突觸元件考量 21
第三章 實驗方法與步驟 28
3-1 實驗敘述與流程說明 28
3-2 實驗設備 29
3-3 元件製備流程 31
3-4 材料分析設備 33
3-5 電性量測分析 35
3-6 模擬系統設備 36
3-7 建構模擬電子突觸各類非理想因子說明 37
第四章 結果與討論 42
4-1 以二氧化鈦作為電阻切換層之基本元件製備 42
4-2 Ni/TiOx/Pt元件基本特性 45
4-3電子突觸元件模擬 53
第五章 結論與未來展望 71
5-1 結論 71
5-2 未來展望 72
參考文獻 74

參考文獻
[1]S. Jain, A. Ranjan, and K. Roy et. al., "Computing in Memory With Spin-Transfer Torque Magnetic RAM", IEEE Transcations on Very Large Scale Integration VLSI Systems, vol. 26, pp. 470-483, Mar. 2018.
[2]J. Zhang, Z. Wang, and N. Verma, "In-Memory Computation of a Machine-Learning Classifier in a Standard 6T SRAM Array", IEEE Journal of Solid-State Circuits, vol. 52, pp. 915-924, Apr. 2017.
[3]W. Kang, H. Wang, and Z. Wang et. al., "In-Memory Processing Paradigm for Bitwise Logic Operations in STT-MRAM", IEEE Transcations on Magnetics, vol. 53, pp. 1-4, Nov. 2017.
[4]L. Ni, H. Huang, and H. Yu, "On-line machine learning accelerator on digital RRAM-crossbar", 2016 IEEE International Symposium on Circuits and Systems (ISCAS), pp.113-116, May 2016.
[5]W. Chen, R. Fang, and M. B Balaban et al., "A CMOS-compatible electronic synapse device based on Cu/SiO2/W programmable metallization cells", Nanotechnology, vol. 27, p. 255202, Jun. 2016.
[6]R. C. Atkinson and R. M. Shiffrin, "HUMAN MEMORY: A PROPOSED SYSTEM AND ITS CONTROL PROCESSES", Psychology of learning and motivation, vol. 2, pp. 7-113, Apr. 1968.
[7]D. O. Hebb, "THE ORGANIZATION OF BEHAVIOR: A NEUROPSYCHOLOGICAL THEORY", Jan. 1949.
[8]D. E. Feldman, "The Spike-Timing Dependence of Plasticity", Neuron, vol. 75, pp. 556-571, Aug. 2012.
[9]F. Bre, J. M. Gimenez, and V. D. Fachinotti, "Prediction of wind pressure coefficients on building surfaces using artificial neural networks", Energy and Buildings, vol. 158, pp. 1429-1441, Jan. 2018.
[10]"https://www.cnblogs.com/ooon/p/5284676.html".
[11]R. Marks, "Methodology platform for prediction of damage events for self-sensing aerospace panels subjected to real loading conditions", Aug. 2016.
[12]F. M. Simanjuntak, D. Panda, and K. H. Wei et. al., "Status and Prospects of ZnO-Based Resistive Switching Memory Devices", Nanoscale Research Letters, vol. 11, p. 368, Aug. 2016.
[13]A. Sebastian, M. Le Gallo, and R. K. Aljameh et. al., "Memory devices and applications for in-memory computing", Nature Nanotechnology, vol. 15, pp. 529-544, Mar. 2020.
[14]G. W. Burr, R. M. Shelby, and S. Sidler et al., "Experimental Demonstration and Tolerancing of a Large-Scale Neural Network (165 000 Synapses) Using Phase-Change Memory as the Synaptic Weight Element", IEEE Transcations on Electron Devices, vol. 62, pp. 3498-3507, Nov. 2015.
[15]Y. Liao, N. Deng, and H. Wu et. al., "Weighted Synapses Without Carry Operations for RRAM-Based Neuromorphic Systems", Frontiers in Neurosci., vol. 12, p. 167, Mar. 2018.
[16]W. Wang, G. Pedretti, and V. Milo et al., "Learning of spatiotemporal patterns in a spiking neural network with resistive switching synapses", Science Advances, vol. 4, p. 4752, Sep. 2018.
[17]M. K. Rahmani, M. H. Kim, and F. Hussain et al., "Memristive and Synaptic Characteristics of Nitride-Based Heterostructures on Si Substrate", Nanomaterials, vol. 10, p. 994, May 2020.
[18]D. Ielmini, "Resistive switching memories based on metal oxides: mechanisms, reliability and scaling", Semiconductor Science Technology, vol. 31, p. 063002, May 2016.
[19]K. Moon, E. Cha, and J. Park et al., "Analog Synapse Device With 5-b MLC and Improved Data Retention for Neuromorphic System", IEEE Electron Device Letters, vol. 37, pp. 1067-1070, Aug. 2016.
[20]J. Park, M. Kwak, and K. Moon et. al., "TiOx-Based RRAM Synapse With 64-Levels of Conductance and Symmetric Conductance Change by Adopting a Hybrid Pulse Scheme for Neuromorphic Computing", IEEE Electron Device Letters, vol. 37, pp. 1559-1562, Dec. 2016.
[21]S. Yu, "Neuro-Inspired Computing With Emerging Nonvolatile Memorys", Proceedings of the IEEE, vol. 106, pp. 260-285, Feb. 2018.
[22]P. Y. Chen, B. Lin, and I. T. Wang et al., "Mitigating effects of non-ideal synaptic device characteristics for on-chip learning", 2015 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), pp. 194-199, Nov. 2015.
[23]C. C. Chang, P. C. Chen, and T. Chou et al., "Mitigating Asymmetric Nonlinear Weight Update Effects in Hardware Neural Network Based on Analog Resistive Synapse", IEEE Jornal on Emerging and Selected Topics in Circuits Systems, vol. 8, pp. 116-124, Mar. 2018.
[24]G. Sassine, D. A. Robayo, and C. Nail et al., "Optimizing Programming Energy for Improved RRAM Reliability for High Endurance Applications", 2018 IEEE International Memory Workshop (IMW), pp. 1-4, May 2018.
[25]M. Zhao, H. Wu, and B. Gao et al., "Characterizing Endurance Degradation of Incremental Switching in Analog RRAM for Neuromorphic Systems", 2018 IEEE International Electron Devices Meeting (IEDM), Dec. 2018.
[26]J. He, Y. Du, and Y. Bai et al., "Facile Formation of Anatase/Rutile TiO2 Nanocomposites with Enhanced Photocatalytic Activity", Molecules, vol. 24, p. 2996, Aug. 2019.
[27]J. Kim, S. Cho, and T. Kim et al., "Mimicking Synaptic Behaviors with Cross-Point Structured TiOx/TiOy-Based Filamentary RRAM for Neuromorphic Applications", Journal of Electrical Engineering & Technology, vol.14, pp.869-875, Mar. 2019.
[28]"https://towardsdatascience.com/deep-learning-framework-power-scores-2018-23607ddf297a".
[29]"https://corochann.com/mnist-dataset-introduction-1138.html".
[30]B. Bharti, S. Kumar, and H. N. Lee et. al., "Formation of oxygen vacancies and Ti3+ state in TiO2 thin film and enhanced optical properties by air plasma treatment", Scientific Reports, vol. 6, p. 32355, Aug. 2016.
[31]N. Zhong, H. Shima, and H. Akinaga, "Rectifying characteristic of Pt/TiOx/metal/Pt controlled by electronegativity", Applied Physics Letters, vol. 96, p. 042107, Jan. 2010.
[32]D. Acharyya, A. Hazra, and P. Bhattacharyya, "A journey towards reliability improvement of TiO2 based Resistive Random Access Memory: A review", Microelectronics Reliability, vol. 54, pp. 541-560, Mar. 2014.
[33]L. Tu, S. Yuan, and J. Xu et al., "A wide-range operating synaptic device based on organic ferroelectricity with low energy consumption", RSC Advance, vol. 8, pp. 26549-26553, May 2018.
[34]R. Zhao, Y. Hu, and J. Dotzel et. al., "Improving Neural Network Quantization without Retraining using Outlier Channel Splitting", p. 09504, May 2019.
[35]A. Goncharenko, A. Denisov, and S. Alyamkin et. al., "Fast Adjustable Threshold For Uniform Neural Network Quantization", p. 07872, Jun. 2019.