Related papers: Power efficient ReLU design for neuromorphic compu…
Neuromorphic computing (NC) architecture has shown its suitability for energy-efficient computation. Amongst several systems, spin-orbit torque (SOT) based domain wall (DW) devices are one of the most energy-efficient contenders for NC. To…
In this study, SoftReMish, a new activation function designed to improve the performance of convolutional neural networks (CNNs) in image classification tasks, is proposed. Using the MNIST dataset, a standard CNN architecture consisting of…
Ferromagnetic (FM)/heavy metal (HM) nanostructures can be used for the magnetic state readout in the proposed magneto-electric spin-orbit logic by locally injecting a spin-polarized current and measure the spin-to-charge conversion via the…
Classification of biological images is an important task with crucial application in many fields, such as cell phenotypes recognition, detection of cell organelles and histopathological classification, and it might help in early medical…
The non-convex nature of trained neural networks has created significant obstacles in their incorporation into optimization models. In this context, Anderson et al. (2020) provided a framework to obtain the convex hull of the graph of a…
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…
Activation functions play a pivotal role in determining the training dynamics and neural network performance. The widely adopted activation function ReLU despite being simple and effective has few disadvantages including the Dying ReLU…
Recently, significant progress has been made in solving sophisticated problems among various domains by using reinforcement learning (RL), which allows machines or agents to learn from interactions with environments rather than explicit…
The electrically readable complex dynamics of robust and scalable magnetic tunnel junctions (MTJs) offer promising opportunities for advancing neuromorphic computing. In this work, we present an MTJ design with a free layer and two…
A general procedure for introducing parametric, learned, nonlinearity into activation functions is found to enhance the accuracy of representative neural networks without requiring significant additional computational resources. Examples…
This is paper for the smooth function approximation by neural networks (NN). Mathematical or physical functions can be replaced by NN models through regression. In this study, we get NNs that generate highly accurate and highly smooth…
An activation function has crucial role in a deep neural network. A simple rectified linear unit (ReLU) are widely used for the activation function. In this paper, a weighted sigmoid gate unit (WiG) is proposed as the activation function.…
The writing energy for reversing the magnetization of the free layer in a magnetic tunnel junction (MTJ) is a key figure of merit for comparing the performances of magnetic random access memories with competing technologies. Magnetization…
We study the approximation properties of shallow neural networks with an activation function which is a power of the rectified linear unit. Specifically, we consider the dependence of the approximation rate on the dimension and the…
The performance of artificial neural networks (ANNs) is influenced by weight initialization, the nature of activation functions, and their architecture. There is a wide range of activation functions that are traditionally used to train a…
This study introduces a novel activation function, characterized by a dynamic slope that adjusts throughout the training process, aimed at enhancing adaptability and performance in deep neural networks for computer vision tasks. The…
Lipschitz-constrained neural networks have many applications in machine learning. Since designing and training expressive Lipschitz-constrained networks is very challenging, there is a need for improved methods and a better theoretical…
Photonic computing chips have made significant progress in accelerating linear computations, but nonlinear computations are usually implemented in the digital domain, which introduces additional system latency and power consumption, and…
Neuromorphic computing aims to replicate the brain's remarkable energy efficiency and parallel processing capabilities for large-scale artificial intelligence applications. In this work, we present a comprehensive comparative study of three…
The Rashba-Edelstein effect (REE), which generates interfacial spin polarization and subsequent spin current, is a compelling spin-charge conversion mechanism for spintronics applications, since it is not limited by the elemental spin-orbit…