└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Stochastic-computing-based-neural-network-accelerator 2 | ## Stochastic Number Generator (SNG) 3 | ### 2012 4 | - 2012 ICCAD: An Efficient Implementation of Numerical Integration Using Logical Computation on Stochastic Bit Streams (University of Michigan–Shanghai Jiao Tong University Joint Institute) 5 | ### 2013 6 | - 2013 ASPDAC: Optimizing Multi-level Combinational Circuits for Generating Random Bits (University of Michigan–Shanghai Jiao Tong University Joint Institute) 7 | ### 2014 8 | - 2014 DATE: Fast and Accurate Computation Using Stochastic Circuits (University of Michigan, Ann Arbor) 9 | ### 2016 10 | - 2016 ICCAD: A Deterministic Approach to Stochastic Computation (University of Minnesota) 11 | - 2016 DATE: Effect of LFSR Seeding, Scrambling and Feedback Polynomial on Stochastic Computing Accuracy (University of Toronto; Tokyo Institute of Technology; Ritsumeikan University) 12 | ### 2017 13 | - 2017 DATE: Energy Efficient Stochastic Computing with Sobol Sequences (University of Alberta) 14 | - 2017 DSD: Building a Better Random Number Generator for Stochastic Computing (University of Passau; University of Michigan, Ann Arbor) 15 | - 2017 ICCAD: Design of Accurate Stochastic Number Generators with Noisy Emerging Devices for Stochastic Computing (University of Michigan–Shanghai Jiao Tong University Joint Institute) 16 | - 2017 IWLS: Design of Reliable Stochastic Number Generators Using Emerging Devices for Stochastic Computing (University of Michigan–Shanghai Jiao Tong University Joint Institute) 17 | ### 2018 18 | - [2018 ICCAD](https://ieeexplore.ieee.org/abstract/document/8587654): Deterministic Methods for Stochastic Computing Using Low-Discrepancy Sequences (University of Louisiana at Lafayette) 19 | - [2018 TCAD](https://ieeexplore.ieee.org/abstract/document/8246551): An Efficient and Accurate Stochastic Number Generator Using Even-Distribution Coding. (NIST, Samsung, SNU) 20 | - [2018 Microprocessors and Microsystems](https://www.sciencedirect.com/science/article/pii/S0141933118300590): S-Box-Based Random Number Generation for Stochastic Computing (University of Passau; University of Michigan, Ann Arbor) 21 | - [2018 TVLSI](https://ieeexplore.ieee.org/abstract/document/8327916): Toward Energy-Efficient Stochastic Circuits Using Parallel Sobol Sequences (University of Alberta) 22 | - 2018 ISVLSI: Towards Theoretical Cost Limit of Stochastic Number Generators for Stochastic Computing (University of Michigan–Shanghai Jiao Tong University Joint Institute) 23 | - [2018 ICRC](https://ieeexplore.ieee.org/abstract/document/8638611): SC-SD: Towards Low Power Stochastic Computing Using Sigma Delta Streams. (University of Virginia Charlottesville) 24 | ### 2019 25 | - [2019 arxiv](https://arxiv.org/pdf/1902.05971.pdf): Synthesizing Number Generators for Stochastic Computing using Mixed Integer Programming. (Washington) 26 | - [2019 TED](https://ieeexplore.ieee.org/abstract/document/8741170):Spin-Hall-Effect-Based Stochastic Number Generator for Parallel Stochastic Computing. (Minnesota) 27 | - [2019 SNW](https://ieeexplore.ieee.org/abstract/document/8782977):A Parallel Bitstream Generator for Stochastic Computing. (Peking) 28 | 29 | 30 | ## Accuracy Analysis 31 | - 2015 GLSVLSI: Minimizing Error of Stochastic Computation through Linear Transformation (University of Michigan–Shanghai Jiao Tong University Joint Institute) 32 | - [2018 JETC](https://dl.acm.org/citation.cfm?id=3183345): Framework for Quantifying and Managing Accuracy in Stochastic Circuit Design (University of Michigan, Ann Arbor) 33 | - [2018 DATE](https://ieeexplore.ieee.org/abstract/document/8342234): Correlation manipulating circuits for stochastic computing. (Washington) 34 | - [2018 ISOCC](https://ieeexplore.ieee.org/abstract/document/8649892): Accurate Stochastic Computing Using a Wire Exchanging Unipolar Multiplier. (Kwangwoon University) 35 | - [2018 ISOCC](https://ieeexplore.ieee.org/abstract/document/8649979): Generalized Adaptive Variable Bit Truncation Method for Approximate Stochastic Computing. (Missouri Univ of Science & Technology, Daegu University, Northeastern) 36 | 37 | 38 | ## Neural Networks 39 | ### 2016 40 | - 2016 DAC: Dynamic Energy-Accuracy Trade-off Using Stochastic Computing in Deep Neural Networks. (Samsung, Seoul National University, Ulsan National Institute of Science and Technology) 41 | ### 2017 42 | - 2017 ASPLOS: SC-DCNN: Highly-Scalable Deep Convolutional Neural Network using Stochastic Computing. (Syracuse University, USC, The City College of New York) 43 | - 2017 DAC: New Stochastic Computing Multiplier and Its Application to Deep Neural Networks. (UNIST) 44 | - 2017 ICCAD: Deep reinforcement learning: Framework, applications, and embedded implementations: Invited paper. (Syracuse, University of California) 45 | - 2017 DATE: Structural Design Optimization for Deep Convolutional Neural Networks Using Stochastic Computing. (Syracuse, USC, CUNY) 46 | - 2017 DATE: Energy-Efficient Hybrid Stochastic-Binary Neural Networks for Near-Sensor Computing. (University of Washington, University of Michigan) 47 | - 2017 DATE: Magnetic tunnel junction enabled all-spin stochastic spiking neural network. (Purdue) 48 | - 2017 ICCD: Accurate and Efficient Stochastic Computing Hardware for Convolutional Neural Networks. (Syracuse, USC, CUNY) 49 | - 2017 ICCD: Neural Network Classifiers Using Stochastic Computing with a Hardware-Oriented Approximate Activation Function. (UMN, CUNY) 50 | - 2017 TVLSI: VLSI Implementation of Deep Neural Network Using Integral Stochastic Computing. (McGill University, Tohoku University) 51 | - 2017 ASP-DAC: Scalable Stochastic-computing Accelerator for Convolutional Neural Networks. (UNIST, Seoul National University) 52 | - 2017 ASP-DAC: Towards Acceleration of Deep Convolutional Neural Networks Using Stochastic Computing. (USC, Syracuse, CUNY) 53 | - 2017 ISLPED: Power optimizations in MTJ-based Neural Networks through Stochastic Computing. (University of Maryland) 54 | - 2017 ISQED: Stochastic-based multi-stage streaming realization of deep convolutional neural network. (University of Central Florida) 55 | - 2017 IJCNN: Hardware-driven nonlinear activation for stochastic computing based deep convolutional neural networks (USC, Syracuse) 56 | - 2017 GLSVLSI: Softmax Regression Design for Stochastic Computing Based Deep Convolutional Neural Networks. (USC, Syracuse, CNNY) 57 | - 2017 WCSP: Efficient fast convolution architecture based on stochastic computing. (LEADS, City University of New York, Southeast) 58 | - 2017 VLSI-DAT: Hybrid spiking-stochastic Deep Neural Network. (Seoul National University) 59 | - 2017 Big Data: Energy efficient stochastic-based deep spiking neural networks for sparse datasets. (Oak Ridge National Laboratory) 60 | - 2017 TCAS-II: Fully-Parallel Area-Efficient Deep Neural Network Design Using Stochastic Computing. (City University of New York, Syracuse, Nanjing University) 61 | - 2017 Integration, the VLSI Journal: Normalization and dropout for stochastic computing-based deep convolutional neural networks. (University of Southern California, Syracuse, City University of New York) 62 | - 2017 International Journal of Approximate Reasoning: Quick and energy-efficient Bayesian computing of binocular disparity using stochastic digital signals. (ISIR) 63 | ### 2018 64 | - [2018 DAC](https://ieeexplore.ieee.org/abstract/document/8465807): **Sign-Magnitude SC: Getting 10X Accuracy for Free in Stochastic Computing for Deep Neural Networks**. (UNIST) 65 | - [2018 DAC](https://dl.acm.org/citation.cfm?id=3196028): DPS: Dynamic Precision Scaling for Stochastic Computing-Based Deep Neural Networks. (UNIST) 66 | - [2018 DATE](https://ieeexplore.ieee.org/abstract/document/8342191): An Energy-efficient Stochastic Computational Deep Belief Network. (Alberta, Syracuse, NEU) 67 | - [2018 ASP-DAC](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8297385): Spintronics based stochastic computing for efficient Bayesian inference system. (Beihang, Duke) 68 | - [2018 FPGA](https://dl.acm.org/citation.cfm?id=3174267): **Routing Magic: Performing Computations Using Routing Networks and Voting Logic on Unary Encoded Data**. (Minnesota) 69 | - 70 | - [2018 TCAD](https://ieeexplore.ieee.org/abstract/document/8403283): HEIF: Highly Efficient Stochastic Computing based Inference Framework for Deep Neural Networks. (Syracuse University, USC, City University of New York) 71 | - [2018 TCAD](https://ieeexplore.ieee.org/abstract/document/8493550): Architecture Considerations for Stochastic Computing Accelerators. (Washington) 72 | - [2018 TCAD](https://ieeexplore.ieee.org/abstract/document/8493588): Gradient Descent Using Stochastic Circuits for Efficient Training of Learning Machines. (University of Alberta, Tsinghua) 73 | - [2018 ISVLSI](https://ieeexplore.ieee.org/abstract/document/8429358): Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks Using Stochastic Computing. (Syracuse, University of Southern California, City University of New York) 74 | - [2018 ISQED](https://ieeexplore.ieee.org/abstract/document/8357316): Quantized Neural Networks with New Stochastic Multipliers. (Minnesota, City University of New York) 75 | - [2018 ISQED](https://ieeexplore.ieee.org/abstract/document/8357306): An area and energy efficient design of domain-wall memory-based deep convolutional neural networks using stochastic computing. (Syracuse, Alberta) 76 | - [2018 ISQED](https://ieeexplore.ieee.org/abstract/document/8357309): Parallel implementation of finite state machines for reducing the latency of stochastic computing. (Minnesota) 77 | - 2018 GLSVLSI: Design Space Exploration of Magnetic Tunnel Junction based Stochastic Computing in Deep Learning. (Beihang) 78 | - [2018 GLSVLSI](https://dl.acm.org/citation.cfm?id=3194620): Bit-Wise Iterative Decoding of Polar Codes using Stochastic Computing. (McGill University) 79 | - 2018 JETC: An FPGA Implementation of a Time Delay Reservoir Using Stochastic Logic. (Air Force Research Laboratory, Rochester Institute of Technology) 80 | - [2018 TETC](https://ieeexplore.ieee.org/abstract/document/8245837): High Quality Down-Sampling for Deterministic Approaches to Stochastic Computing. (Minnesota) 81 | - [2018 Computer Architecture Letters](https://ieeexplore.ieee.org/abstract/document/8289355): **On Memory System Design for Stochastic Computing**. (Minnesota) 82 | - [2018 Transactions on Computers](https://ieeexplore.ieee.org/abstract/document/8319953): A Stochastic Computational Multi-Layer Perceptron with Backward Propagation. (Alberta, Syracuse, Northeastern) 83 | - [2018 DSC](https://ieeexplore.ieee.org/abstract/document/8625153): Stochastic Processors on FPGAs to Compute Sensor Data Towards Fault-Tolerant IoT Systems. (INESC-ID) 84 | - [2018 JESTCS](https://ieeexplore.ieee.org/abstract/document/8403221): An Energy-Efficient Online-Learning Stochastic Computational Deep Belief Network. (Alberta, Syracuse) 85 | - [2018 ACSSC](https://ieeexplore.ieee.org/abstract/document/8645529): Area-efficient K-Nearest Neighbor Design using Stochastic Computing. (Rutgers University) 86 | - [2018 DSP](https://ieeexplore.ieee.org/abstract/document/8631556): Low-Complexity Winograd Convolution Architecture Based on Stochastic Computing. (LEADS, Southeast) 87 | - [2018 APCCAS](https://ieeexplore.ieee.org/abstract/document/8605569): Low Cost LSTM Implementation based on Stochastic Computing for Channel State Information Prediction. (University of Electronic Science and Technology of China) 88 | - 2018 MCSoC: An Efficient Hardware Implementation of Activation Functions Using Stochastic Computing for Deep Neural Networks. (Le Quy Don Technical University) 89 | - 2018 Journal of Low Power Electronics: Optimization of Softmax Layer in Deep Neural Network Using Integral Stochastic Computation. ( Tsinghua) 90 | - 2018 NICS: An Efficient Hardware Implementation of Artificial Neural Network based on Stochastic Computing. (SISLAB) 91 | - 2018 Transactions on Multi-Scale Computing Systems: Scalable FPGA Accelerator for Deep Convolutional Neural Networks with Stochastic Streaming. (Oak Ridge National Laboratory, University of Central Florida) 92 | - 2018 Neurocomputing: Stochastic learning in deep neural networks based on nanoscale PCMO device characteristics. (New Jersey Institute of Technology, Indian Institute of Technology) 93 | - 2018 European Physical Journal Plus: A new stochastic computing paradigm for the dynamics of nonlinear singular heat conduction model of the human head. (Institute of Information Technology, HITEC University, Cankaya University) 94 | - 2018 IEICE: Application of stochastic computing in brainware. (McGill University, Tohoku University) 95 | - [2018 CSIT](https://ieeexplore.ieee.org/abstract/document/8526729): Feature Selection Based on Parallel Stochastic Computing. (Zaporizhzhia National Technical University) 96 | 97 | 98 | 99 | ### 2019 100 | - [2019 DAC](http://delivery.acm.org/10.1145/3320000/3317911/a132-Hojabr.pdf?ip=162.105.201.72&id=3317911&acc=ACTIVE%20SERVICE&key=BF85BBA5741FDC6E%2EAC95BC9DA5A3FA7E%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1570457259_36f47615d31bf32ee46a7359082491ef): SkippyNN: An Embedded Stochastic-computing Accelerator forConvolutional Neural Networks. (Univ. of Tehran, Minnesota) 101 | - [2019 DAC](https://dl.acm.org/citation.cfm?id=3317845): LAcc: Exploiting Lookup Table-based Fast and Accurate Vector Multiplication in DRAM-based CNN Accelerator. (National Univ. of Defense Technology, Pittsburgh) 102 | - [2019 DAC](https://dl.acm.org/citation.cfm?id=3317916): Successive Log Quantization for Cost-Efficient Neural Networks Using Stochastic Computing. (UNIST) 103 | - [2019 DAC](https://dl.acm.org/citation.cfm?id=3317844): In-Stream Stochastic Division and Square Root via Correlation. (Wisconsin-Madison) 104 | - 2019 DATE: Energy-Efficient Convolutional Neural Networks with Deterministic Bit-Stream Processing. (University of Minnesota, University of Louisiana) 105 | - [2019 ASP-DAC](https://dl.acm.org/citation.cfm?id=3287714): Log-quantized stochastic computing for memory and computation efficient DNNs. (UNIST) 106 | - [2019 ASP-DAC](https://dl.acm.org/citation.cfm?id=3287706): Hybrid binary-unary hardware accelerator. (Minnesota) 107 | - [2019 TCAS-I](https://ieeexplore.ieee.org/abstract/document/8610326): Efficient CMOS Invertible Logic Using Stochastic Computing. (McGill University, Tohoku University) 108 | - [2019 TCAS-II](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8671762): New Divider Design for Stochastic Computing. 109 | - [2019 TCAS-II](https://ieeexplore.ieee.org/abstract/document/8713530): A stochastic computing architecture for iterative estimation. (Johannes Kepler Universit) 110 | - [2019 TCAS-II](https://ieeexplore.ieee.org/abstract/document/8700272): High-Accuracy and Fault Tolerant Stochastic Inner Product Design. () 111 | - [2019 TCAD](https://ieeexplore.ieee.org/document/8634932): SPINBIS: Spintronics based Bayesian Inference System with Stochastic Computing. (Beihang, University of South California, Duke) 112 | - [2019 JETC](https://dl.acm.org/citation.cfm?id=3309882): Low-Cost Stochastic Hybrid Multiplier for Quantized Neural Networks. (Minnesota, University of Louisiana at Lafayette) 113 | - [2019 JETC](https://dl.acm.org/citation.cfm?id=3284933): Neural Network Classifiers Using a Hardware-Based Approximate Activation Function with a Hybrid Stochastic Multiplier. (Minnesota, Rutgers University) 114 | - [2019 VLSI System](https://ieeexplore.ieee.org/abstract/document/8630962): Design of FSM-Based Function With Reduced Number of States in Integral Stochastic Computing. (National Kaohsiung University of Science and Technology) 115 | - 2019 arXiv: From Stochastic to Bit Stream Computing: Accurate Implementation of Arithmetic Circuits and Applications in Neural Networks. (Istanbul Technical University) 116 | - [2019 AAAI](https://www.aaai.org/ojs/index.php/AAAI/article/view/4475): Universal Approximation Property and Equivalence of Stochastic Computing-Based Neural Networks and Binary Neural Networks. (Northeastern, Syracuse) 117 | - [2019 CF](http://delivery.acm.org/10.1145/3330000/3323050/p59-neugebauer.pdf?ip=162.105.201.72&id=3323050&acc=ACTIVE%20SERVICE&key=BF85BBA5741FDC6E%2EAC95BC9DA5A3FA7E%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1570455004_1f7bcab9685100d9446c9819fd6ae717): On the maximum function in stochastic computing. (Stuttgart, Michigan) 118 | - [2019 Access](https://ieeexplore.ieee.org/abstract/document/8731879): Stochastic Computing for Hardware Implementation of Binarized Neural Networks. () 119 | - [2019 TVLSI](https://ieeexplore.ieee.org/abstract/document/8746640): An Energy-Efficient and Noise-Tolerant Recurrent Neural Network Using Stochastic Computing. (Alberta, Tsinghua, Northeastern) SC+RNN 120 | - [2019 ISCAS](https://ieeexplore.ieee.org/abstract/document/8702248): Stochastic Computing for Low-Power and High-Speed Deep Learning on FPGA. (James Cook University) SC online training accelerator 121 | - [2019 ASAP](https://ieeexplore.ieee.org/abstract/document/8825149): Efficient Architectures and Implementation of Arithmetic Functions Approximation Based Stochastic Computing. (University College Cork) 122 | - [2019 ASAP](https://ieeexplore.ieee.org/abstract/document/8825119): Context-Aware Number Generator for Deterministic Bit-stream Computing. (Louisiana at Lafayette) 123 | - [2019 ASAP](https://ieeexplore.ieee.org/abstract/document/8825135): Energy-Efficient Near-Sensor Convolution using Pulsed Unary Processing. (Louisiana at Lafayette, Minnesota) 124 | - [2019 ASAP](https://ieeexplore.ieee.org/abstract/document/8825100): Using Residue Number Systems to Accelerate Deterministic Bit-stream Multiplication. (University of Tehran, Louisiana at Lafayette, IPM, Shahid Beheshti University, IROST) 125 | - [2019 GLSVLSI](http://delivery.acm.org/10.1145/3320000/3317985/p51-erlina.pdf?ip=162.105.201.72&id=3317985&acc=ACTIVE%20SERVICE&key=BF85BBA5741FDC6E%2EAC95BC9DA5A3FA7E%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1570458184_a42a147c5b2f67b759bf31889ce4de47): An Efficient Time-based Stochastic Computing Circuitry Employing Neuron-MOS. (NAIST) 126 | - [2019 GLSVLSI](https://dl.acm.org/citation.cfm?id=3317989): Low Cost Hybrid Spin-CMOS Compressor for Stochastic Neural Networks. (Minnesota) 127 | - [2019 ISQED](https://ieeexplore.ieee.org/abstract/document/8697443): Accelerating Deterministic Bit-Stream Computing with Resolution Splitting. (University of Louisiana, University of Minnesota) 128 | - [2019 ISQED](https://ieeexplore.ieee.org/abstract/document/8697451): Deterministic Stochastic Computation Using Parallel Datapaths. (Texas at Austin) 129 | - [2019 VLSID](https://ieeexplore.ieee.org/abstract/document/8710820): Reducing the Overhead of Stochastic Number Generators Without Increasing Error. (Ritsumeikan University) 130 | - [2019 Neural Networks](https://www.sciencedirect.com/science/article/pii/S0893608019301236): Cost-effective stochastic MAC circuits for deep neural networks. (UNIST) 131 | - [2019 LCTES](https://dl.acm.org/citation.cfm?id=3326355): BitBench: a benchmark for bitstream computing. (Wisconsin-Madison) 132 | - [2019 International Journal of Approximate Reasoning](https://www.sciencedirect.com/science/article/pii/S0888613X18304213): Bayesian inference using stochastic logic: A study of buffering schemes for mitigating autocorrelation. (Loyola University Maryland) 133 | - [2019 Neuroscience](https://www.frontiersin.org/articles/10.3389/fnins.2019.00189/full): ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing. (Purdue) 134 | - [2019 ICASSP](https://ieeexplore.ieee.org/abstract/document/8683521): Stochastic Data-driven Hardware Resilience to Efficiently Train Inference Models for Stochastic Hardware Implementations. (Princeton) MRAM-PIM 135 | - [2019 arxiv](https://arxiv.org/pdf/1909.09153.pdf): Density Encoding Enables Resource-Efficient Randomly Connected Neural Networks. (Luleå University of Technology, Berkeley) 136 | - [2019](https://www.researchgate.net/profile/Amin_Norollah/publication/334732950_A_New_Hardware_Accelerator_for_Data_Sorting_in_Area_Energy_Constrained_Architectures/links/5d3deba2a6fdcc370a69421e/A-New-Hardware-Accelerator-for-Data-Sorting-in-Area-Energy-Constrained-Architectures.pdf): A New Hardware Accelerator for Data Sorting in Area & Energy Constrained Architectures. (Iran University of Science & Technology) 137 | - [2019 Electronics](https://www.mdpi.com/2079-9292/8/6/720/htm): Novel Stochastic Computing for Energy-Efficient Image Processors. (Kwangwoon University, Hongik University) 138 | 139 | 140 | 141 | 142 | 143 | 144 | 145 | 146 | 147 | 148 | 149 | 150 | 151 | 152 | 153 | 154 | --------------------------------------------------------------------------------