TY - JOUR

T1 - A Spiking Recurrent Neural Network With Phase-Change Memory Neurons and Synapses for the Accelerated Solution of Constraint Satisfaction Problems

AU - Pedretti, Giacomo

AU - Mannocci, Piergiulio

AU - Hashemkhani, Shahin

AU - Milo, Valerio

AU - Melnic, Octavian

AU - Chicca, Elisabetta

AU - Ielmini, Daniele

PY - 2020/6

Y1 - 2020/6

N2 - Data-intensive computing applications, such as object recognition, time series prediction, and optimization tasks, are becoming increasingly important in several fields, including smart mobility, health, and industry. Because of the large amount of data involved in the computation, the conventional von Neumann architecture suffers from excessive latency and energy consumption due to the memory bottleneck. A more efficient approach consists of in-memory computing (IMC), where computational operations are directly carried out within the data. IMC can take advantage of the rich physics of memory devices, such as their ability to store analog values to be used in matrix-vector multiplication (MVM) and their stochasticity that is highly valuable in the frame of optimization and constraint satisfaction problems (CSPs). This article presents a stochastic spiking neuron based on a phase-change memory (PCM) device for the solution of CSPs within a Hopfield recurrent neural network (RNN). In the RNN, the PCM cell is used as the integrating element of a stochastic neuron, supporting the solution of a typical CSP, namely a Sudoku puzzle in hardware. Finally, the ability to solve Sudoku puzzles using RNNs with PCM-based neurons is studied for increasing size of Sudoku puzzles by a compact simulation model, thus supporting our PCM-based RNN for data-intensive computing.

AB - Data-intensive computing applications, such as object recognition, time series prediction, and optimization tasks, are becoming increasingly important in several fields, including smart mobility, health, and industry. Because of the large amount of data involved in the computation, the conventional von Neumann architecture suffers from excessive latency and energy consumption due to the memory bottleneck. A more efficient approach consists of in-memory computing (IMC), where computational operations are directly carried out within the data. IMC can take advantage of the rich physics of memory devices, such as their ability to store analog values to be used in matrix-vector multiplication (MVM) and their stochasticity that is highly valuable in the frame of optimization and constraint satisfaction problems (CSPs). This article presents a stochastic spiking neuron based on a phase-change memory (PCM) device for the solution of CSPs within a Hopfield recurrent neural network (RNN). In the RNN, the PCM cell is used as the integrating element of a stochastic neuron, supporting the solution of a typical CSP, namely a Sudoku puzzle in hardware. Finally, the ability to solve Sudoku puzzles using RNNs with PCM-based neurons is studied for increasing size of Sudoku puzzles by a compact simulation model, thus supporting our PCM-based RNN for data-intensive computing.

KW - Phase change memory (PCM)

KW - artificial synapses

KW - hopfield neural network

KW - stochastic process

KW - optimization

KW - PART I

KW - STATISTICAL FLUCTUATIONS

KW - NOISE

U2 - 10.1109/JXCDC.2020.2992691

DO - 10.1109/JXCDC.2020.2992691

M3 - Article

VL - 6

SP - 89

EP - 97

JO - Ieee journal on exploratory solid-State computational devices and circuits

JF - Ieee journal on exploratory solid-State computational devices and circuits

SN - 2329-9231

IS - 1

M1 - 9086758

ER -