Related papers: Temporal credit assignment for one-shot learning u…
Crossbar array architecture is an essential design element for densely connected Non-Volatile Memory(NVM) applications. To overcome intrinsic sneak current problem of crossbar arrays, each memory unit is serially attached to a selector unit…
Spatial phase inhomogeneity at the nano- to microscale is widely observed in strongly-correlated electron materials. The underlying mechanism and possibility of artificially controlling the phase inhomogeneity are still open questions of…
Neuromorphic computing has recently gained momentum with the emergence of various neuromorphic processors. As the field advances, there is an increasing focus on developing training methods that can effectively leverage the unique…
This paper introduces an analog spiking neuron that utilizes time-domain information, i.e., a time interval of two signal transitions and a pulse width, to construct a spiking neural network (SNN) for a hardware-friendly physical reservoir…
The deployment of Artificial Intelligence on edge devices (TinyML) is often constrained by the high power consumption and latency associated with traditional Artificial Neural Networks (ANNs) and their reliance on intensive Matrix-Multiply…
First-order phase transitions in solids are notoriously challenging to study. The combination of change in unit cell shape, long range of elastic distortion, and flow of latent heat leads to large energy barriers resulting in domain…
Magnetic skyrmions, as scalable and non-volatile spin textures, can dynamically interact with fields and currents, making them promising for unconventional computing. This paper presents a neuromorphic device based on skyrmion manipulation…
We study associative memory neural networks based on the Hodgkin-Huxley type of spiking neurons. We introduce the spike-timing-dependent learning rule, in which the time window with the negative part as well as the positive part is used to…
Changing the interlayer exchange coupling between magnetic layers in-situ is a key issue of spintronics, as it allows for the optimization of properties that are desirable for applications, including magnetic sensing and memory. In this…
Biologically-inspired Spiking Neural Networks (SNNs), processing information using discrete-time events known as spikes rather than continuous values, have garnered significant attention due to their hardware-friendly and energy-efficient…
Thermodynamic-driven filament formation in redox-based resistive memory and the impact of thermal fluctuations on switching probability of emerging magnetic switches are probabilistic phenomena in nature, and thus, processes of binary…
We present an experimental demonstration of passive, dynamic thermal regulation in a solid-state system with temperature-dependent thermal emissivity switching. We achieve this effect using a multilayered device, comprised of a vanadium…
Hyperparameters and learning algorithms for neuromorphic hardware are usually chosen by hand. In contrast, the hyperparameters and learning algorithms of networks of neurons in the brain, which they aim to emulate, have been optimized…
Spiking neural networks (SNNs) that enable low-power design on edge devices have recently attracted significant research. However, the temporal characteristic of SNNs causes high latency, high bandwidth and high energy consumption for the…
Spiking neural networks (SNNs) promise energy-efficient computation by mimicking biological neural dynamics, yet existing plasticity rules focus on isolated spike pairs and fail to leverage the synchronous activity patterns that drive…
In this work, we report the design of a wavelength-tunable infrared metamaterial by exciting magnetic resonance with phase transition of vanadium dioxide (VO2). Numerical simulation shows a broad absorption peak at the wavelength of 10.9 um…
The optical properties of vanadium dioxide ($VO_2$) can be tuned via metal-insulator transition. In this work different types of one-dimensional photonic structure-based microcavities that embed vanadium dioxide have been studied in the…
Spiking Neural Networks (SNNs) can do inference with low power consumption due to their spike sparsity. ANN-SNN conversion is an efficient way to achieve deep SNNs by converting well-trained Artificial Neural Networks (ANNs). However, the…
Spiking recurrent neural networks (RNNs) are a promising tool for solving a wide variety of complex cognitive and motor tasks, due to their rich temporal dynamics and sparse processing. However training spiking RNNs on dedicated…
Advances in neuroscience uncover the mechanisms employed by the brain to efficiently solve complex learning tasks with very limited resources. However, the efficiency is often lost when one tries to port these findings to a silicon…