A hardware Markov chain algorithm realized in a single device for machine learning

There is a growing need for developing machine learning applications. However, implementation of the machine learning algorithm consumes a huge number of transistors or memory devices on-chip. Developing a machine learning capability in a single device has so far remained elusive. Here, we build a Markov chain algorithm in a single device based on the native oxide of two dimensional multilayer tin selenide. After probing the electrical transport in vertical tin oxide/tin selenide/tin oxide heterostructures, two sudden current jumps are observed during the set and reset processes. Furthermore, five filament states are observed. After classifying five filament states into three states of the Markov chain, the probabilities between each states show convergence values after multiple testing cycles. Based on this device, we demo a fixed-probability random number generator within 5% error rate. This work sheds light on a single device as one hardware core with Markov chain algorithm.Despite the need to develop resistive random access memory (RRAM) devices for machine learning, RRAM array-based hardware methods for algorithm require external electronics. Here, the authors realize a Markov chain algorithm in a single 2D multilayer SnSe device without external electronics.

[1]  R. Fang,et al.  Low-Temperature Characteristics of HfOx-Based Resistive Random Access Memory , 2015, IEEE Electron Device Letters.

[2]  Jianxin Wu.  Hidden Markov model , 2018 .

[3]  Richard Martel,et al.  Photooxidation and quantum confinement effects in exfoliated black phosphorus. , 2015, Nature materials.

[4]  Rainer Waser,et al.  Complementary resistive switches for passive nanocrossbar memories. , 2010, Nature materials.

[5]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[6]  H-S Philip Wong,et al.  Memory leads the way to better computing. , 2015, Nature nanotechnology.

[7]  Heng Wang,et al.  Ultrahigh power factor and thermoelectric performance in hole-doped single-crystal SnSe , 2016, Science.

[8]  A. Radenović,et al.  Single-layer MoS2 transistors. , 2011, Nature nanotechnology.

[9]  R. Waser,et al.  Nanoionics-based resistive switching memories. , 2007, Nature materials.

[10]  K Watanabe,et al.  Quality Heterostructures from Two-Dimensional Crystals Unstable in Air by Their Assembly in Inert Atmosphere. , 2015, Nano letters.

[11]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[12]  Takashi Taniguchi,et al.  Air-stable transport in graphene-contacted, fully encapsulated ultrathin black phosphorus-based field-effect transistors. , 2015, ACS nano.

[13]  J. Tour,et al.  Highly transparent nonvolatile resistive memory devices from silicon oxide and graphene , 2012, Nature Communications.

[14]  A. Geim,et al.  Two-dimensional gas of massless Dirac fermions in graphene , 2005, Nature.

[15]  K. Novoselov,et al.  A roadmap for graphene , 2012, Nature.

[16]  Julio Gómez-Herrero,et al.  2D materials: to graphene and beyond. , 2011, Nanoscale.

[17]  A. Bessonov,et al.  Layered memristive and memcapacitive switches for printable electronics. , 2015, Nature materials.

[18]  Hongzheng Chen,et al.  Graphene-like two-dimensional materials. , 2013, Chemical reviews.

[19]  Nicolas Locatelli,et al.  Learning through ferroelectric domain dynamics in solid-state synapses , 2017, Nature Communications.

[20]  R. Gorbachev.  Van der Waals heterostructures , 2014, Nature Reviews Methods Primers.

[21]  Stefano Ambrogio,et al.  True Random Number Generation by Variability of Resistive Switching in Oxide-Based Devices , 2015, IEEE Journal on Emerging and Selected Topics in Circuits and Systems.

[22]  Minoru Osada,et al.  Two‐Dimensional Dielectric Nanosheets: Novel Nanoelectronics From Nanocrystal Building Blocks , 2012, Advanced materials.

[23]  M. Kanatzidis,et al.  Ultralow thermal conductivity and high thermoelectric figure of merit in SnSe crystals , 2014, Nature.

[24]  Ya-Chin King,et al.  A Contact-Resistive Random-Access-Memory-Based True Random Number Generator , 2012, IEEE Electron Device Letters.

[25]  Wei D. Lu,et al.  Sparse coding with memristor networks. , 2017, Nature nanotechnology.

[26]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[27]  Takuji Nishimura,et al.  Mersenne twister: a 623-dimensionally equidistributed uniform pseudo-random number generator , 1998, TOMC.

[28]  L. Lauhon,et al.  Gate-tunable memristive phenomena mediated by grain boundaries in single-layer MoS2. , 2015, Nature nanotechnology.

[29]  James M. Tour,et al.  In situ imaging of the conducting filament in a silicon oxide resistive switch , 2012, Scientific reports.

[30]  Likai Li,et al.  Black phosphorus field-effect transistors. , 2014, Nature nanotechnology.

[31]  C. N. Lau,et al.  The mechanism of electroforming of metal oxide memristive switches , 2009, Nanotechnology.

[32]  Tak Kuen Siu,et al.  Markov Chains: Models, Algorithms and Applications , 2006 .

[33]  Farnood Merrikh-Bayat,et al.  Training and operation of an integrated neuromorphic network based on metal-oxide memristors , 2014, Nature.

[34]  Jing Guo,et al.  Atomically Thin Femtojoule Memristive Device , 2017, Advanced materials.

[35]  Wynne W. Chin,et al.  A Partial Least Squares Latent Variable Modeling Approach for Measuring Interaction Effects: Results from a Monte Carlo Simulation Study and an Electronic - Mail Emotion/Adoption Study , 2003, Inf. Syst. Res..

[36]  Madan Dubey,et al.  Silicene field-effect transistors operating at room temperature. , 2015, Nature nanotechnology.