Composable Probabilistic Inference Networks Using MRAM-based Stochastic Neurons

Abstract

Magnetoresistive random access memory (MRAM) technologies with thermally unstable nanomagnets are leveraged to develop an intrinsic stochastic neuron as a building block for restricted Boltzmann machines (RBMs) to form deep belief networks (DBNs). The embedded MRAM-based neuron is modeled using precise physics equations. The simulation results exhibit the desired sigmoidal relation between the input voltages and probability of the output state. A probabilistic inference network simulator (PIN-Sim) is developed to realize a circuit-level model of an RBM utilizing resistive crossbar arrays along with differential amplifiers to implement the positive and negative weight values. The PIN-Sim is composed of five main blocks to train a DBN, evaluate its accuracy, and measure its power consumption. The MNIST dataset is leveraged to investigate the energy and accuracy tradeoffs of seven distinct network topologies in SPICE using the 14nm HP-FinFET technology library with the nominal voltage of 0.8V, in which an MRAM-based neuron is used as the activation function. The software and hardware level simulations indicate that a $784\times 200\times 10$ topology can achieve less than 5% error rates with $\sim 400pJ$ energy consumption. The error rates can be reduced to 2.5% by using a $784\times 500\times 500\times 500\times 10$ DBN at the cost of $\sim 10\times$ higher energy consumption and significant area overhead. Finally, the effects of specific hardware-level parameters on power dissipation and accuracy tradeoffs are identified via the developed PIN-Sim framework.

References in corpus (3)

• Stochastic Spiking Neural Networks Enabled by Magnetic Tunnel Junctions: From Nontelegraphic to Telegraphic Switching Regimes
• Low-Energy Deep Belief Networks using Intrinsic Sigmoidal Spintronic-based Probabilistic Neurons
• Training a Probabilistic Graphical Model with Resistive Switching Electronic Synapses

Cited by in corpus (7)

• The promise of spintronics for unconventional computing
• Low Barrier Magnet Design for Efficient Hardware Binary Stochastic Neurons
• Autonomous Probabilistic Coprocessing with Petaflips per Second
• Scalable Emulation of Sign-Problem$-$Free Hamiltonians with Room Temperature p-bits
• Analog Signal Processing Using Stochastic Magnets
• Training of Quantized Deep Neural Networks using a Magnetic Tunnel Junction-Based Synapse
• Ground-State Probabilistic Logic with the Simplest Binary Energy Landscape for Probabilistic Computing