Related papers: Low Barrier Magnet Design for Efficient Hardware B…
The concept of perpendicular shape anisotropy spin-transfer torque magnetic random-access memory (PSA-STT-MRAM) consists in increasing the storage layer thickness to values comparable to the cell diameter, to induce a perpendicular shape…
A new approach to increase the downsize scalability of perpendicular STT-MRAM is presented. It consists in significantly increasing the thickness of the storage layer in out-of-plane magnetized tunnel junctions (pMTJ) as compared to…
Biologically-inspired computing models have made significant progress in recent years, but the conventional von Neumann architecture is inefficient for the large-scale matrix operations and massive parallelism required by these models. This…
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…
We report a spin-orbit torque(SOT) magnetoresistive random-access memory(MRAM)-based probabilistic binary neural network(PBNN) for resource-saving and hardware noise-tolerant computing applications. With the presence of thermal fluctuation,…
Bayesian Neural Networks (BNNs) provide superior estimates of uncertainty by generating an ensemble of predictive distributions. However, inference via ensembling is resource-intensive, requiring additional entropy sources to generate…
Bayesian Neural Networks (BNNs) can overcome the problem of overconfidence that plagues traditional frequentist deep neural networks, and are hence considered to be a key enabler for reliable AI systems. However, conventional hardware…
We present a design-scheme for ultra-low power neuromorphic hardware using emerging spin-devices. We propose device models for 'neuron', based on lateral spin valves and domain wall magnets that can operate at ultra-low terminal voltage of…
Spintronics-based nonvolatile components in neuromorphic circuits offer the possibility of realizing novel functionalities at low power. Current-controlled electrical switching of magnetization is actively researched in this context.…
Recent years have witnessed growing interest in the field of brain-inspired computing based on neural-network architectures. In order to translate the related algorithmic models into powerful, yet energy-efficient cognitive-computing…
The design of systems implementing low precision neural networks with emerging memories such as resistive random access memory (RRAM) is a major lead for reducing the energy consumption of artificial intelligence (AI). Multiple works have…
Biologically inspired recurrent neural networks, such as reservoir computers are of interest in designing spatio-temporal data processors from a hardware point of view due to the simple learning scheme and deep connections to Kalman…
Probabilistic (p-) bits implemented with low energy barrier nanomagnets (LBMs) have recently gained attention because they can be leveraged to perform some computational tasks very efficiently. Although more error-resilient than Boolean…
Long Short-Term Memory (LSTM) is one of the most widely used recurrent structures in sequence modeling. It aims to use gates to control information flow (e.g., whether to skip some information or not) in the recurrent computations, although…
To make a useful STT-MRAM (spin-transfer torque magnetoresistive random-access memory) device, it is necessary to be able to calculate switching rates, which determine the error rates of the device. In a single-macrospin model, one can use…
Stochastic spiking neural networks based on nanoelectronic spin devices can be a possible pathway to achieving "brainlike" compact and energy-effcient cognitive intelligence. The computational model attempt to exploit the intrinsic device…
Single-molecule magnets (SMMs) are promising elements for quantum informatics. In the presence of strong magnetic anisotropy, they exhibit magnetization blocking - a magnetic memory effect at the level of a single molecule. Recent studies…
Spin-orbit torque (SOT) is a promising switching mechanism for magnetic random-access memory (MRAM) as a result of the potential for improved switching speed and energy-efficiency. It is of particular interest to develop an SOT-MRAM device…
State-of-the-Art (SotA) hardware implementations of Deep Neural Networks (DNNs) incur high latencies and costs. Binary Neural Networks (BNNs) are potential alternative solutions to realize faster implementations without losing accuracy. In…
Neural networks for industrial applications generally have additional constraints such as response speed, memory size and power usage. Randomized learners can address some of these issues. However, hardware solutions can provide better…