Spin-Hall MTJ Cells for Intra-Column Competition in Hierarchical Temporal Memory

We propose a dedicated winner-take-all circuit to efficiently implement the intra-column competition between cells in Hierarchical Temporal Memory which is a crucial part of the algorithm. All inputs and outputs are charge-based for compatibility with standard CMOS. The circuit incorporates memristors for competitive advantage to emulate a column with a cell in a predictive state. The circuit can also detect columns bursting by passive averaging and comparison of the cell outputs. The proposed spintronic devices and circuit are thoroughly described and a series of simulations are used to predict the performance. The simulations indicate that the circuit can complete a nine-cell, nine-input competition operation in under 15 ns at a cost of about 25 pJ.

SHE-MTJ Circuits for Convolutional Neural Networks

We report the performance characteristics of a notional Convolutional Neural Network based on the previously-proposed Multiply-Accumulate-Activate-Pool set, an MTJ-based spintronic circuit made to compute multiple neural functionalities in parallel. A study of image classification with the MNIST handwritten digits dataset using this network is provided via simulation. The effect of changing the weight representation precision, the severity of device process variation within the MAAP sets and the computational redundancy are provided. The emulated network achieves between 90 and 95% image classification accuracy at a cost of ~100 nJ per image.

Nonvolatile Spintronic Memory Cells for Neural Networks

A new spintronic nonvolatile memory cell analogous to 1T DRAM with non-destructive read is proposed. The cells can be used as neural computing units. A dual-circuit neural network architecture is proposed to leverage these devices against the complex operations involved in convolutional networks. Simulations based on HSPICE and Matlab were performed to study the performance of this architecture when classifying images as well as the effect of varying the size and stability of the nanomagnets. The spintronic cells outperform a purely charge-based implementation of the same network, consuming about 100 pJ total per image processed.

Convolutional Neural Networks Utilizing Multifunctional Spin-Hall MTJ Neurons

We propose a new network architecture for standard spin-Hall magnetic tunnel junction-based spintronic neurons that allows them to compute multiple critical convolutional neural network functionalities simultaneously and in parallel, saving space and time. An approximation to the Rectified Linear Unit transfer function and the local pooling function are computed simultaneously with the convolution operation itself. A proof-of-concept simulation is performed on the MNIST dataset, achieving up to 98% accuracy at a cost of less than 1 nJ for all convolution, activation and pooling operations combined. The simulations are remarkably robust to thermal noise, performing well even with very small magnetic layers.

Benchmarking Inverse Rashba-Edelstein Magnetoelectric Devices for Neuromorphic Computing

We propose a new design for a cellular neural network with spintronic neurons and CMOS-based synapses. Harnessing the magnetoelectric and inverse Rashba-Edelstein effects allows natural emulation of the behavior of an ideal cellular network. This combination of effects offers an increase in speed and efficiency over other spintronic neural networks. A rigorous performance analysis via simulation is provided.

Evaluation of Ionospheric Densities Using Coincident OII 83.4 nm Airglow and the Millstone Hill Radar

We test the utility of the OII 83.4 nm emission feature as a measure of ionospheric parameters. Observed with the Remote Atmospheric and Ionospheric Detection System (RAIDS) Extreme Ultraviolet Spectrograph on the International Space Station (ISS), limb profiles of 83.4 nm emissions are compared to predicted dayglow emission profiles from a theoretical model incorporating ground-based electron density profiles measured by the Millstone Hill radar and parameterized by a best-fit Chapman-{alpha} function. Observations and models are compared for periods of conjunction between Millstone Hill and the RAIDS fields-of-view. These RAIDS observations show distinct differences in topside morphology between two days, 15 January and 10 March 2010, closely matching the forward model morphology and demonstrating that 83.4 nm emission is sensitive to changes in the ionospheric density profile from the 340 km altitude of the ISS during solar minimum. We find no significant difference between 83.4 nm emission profiles modeled assuming a constant scale height Chapman-{alpha} best-fit to the ISR measurements and those assuming varying scale height.