Reconfigurable Stochastic neurons based on tin oxide/MoS2 hetero-memristors for simulated annealing and the Boltzmann machine

Boltzmann Machines offer the potential of more efficient solutions to combinatorial problems compared to von Neumann computing architectures. Here, Yan et al introduce a stochastic memristor with dynamically tunable properties, a vital feature for the efficient implementation of a Boltzmann Machine. Neuromorphic hardware implementation of Boltzmann Machine using a network of stochastic neurons can allow non-deterministic polynomial-time (NP) hard combinatorial optimization problems to be efficiently solved. Efficient implementation of such Boltzmann Machine with simulated annealing desires the statistical parameters of the stochastic neurons to be dynamically tunable, however, there has been limited research on stochastic semiconductor devices with controllable statistical distributions. Here, we demonstrate a reconfigurable tin oxide (SnOx)/molybdenum disulfide (MoS2) heterogeneous memristive device that can realize tunable stochastic dynamics in its output sampling characteristics. The device can sample exponential-class sigmoidal distributions analogous to the Fermi-Dirac distribution of physical systems with quantitatively defined tunable temperature effect. A BM composed of these tunable stochastic neuron devices, which can enable simulated annealing with designed cooling strategies, is conducted to solve the MAX-SAT, a representative in NP-hard combinatorial optimization problems. Quantitative insights into the effect of different cooling strategies on improving the BM optimization process efficiency are also provided.

Automated summary

Boltzmann Machines and hardware implementations with stochastic neurons are effective in solving combinatorial optimization problems, but require dynamically tunable statistical parameters. The authors demonstrate a reconfigurable heterogeneous memristive device with tunable stochastic dynamics in output sampling characteristics.