While Graph Neural Networks (GNNs) have demonstrated their efficacy in dealing with non-
Euclidean structural data, they are difficult to be deployed in real applications due to the …

In this paper, we first define a measure of statistical sensitivity of a zero-order Takagi–
Sugeno (TS) fuzzy neural network (FNN) with respect to perturbation of weights and …

Winograd is generally utilized to optimize convolution performance and computational
efficiency because of the reduced multiplication operations, but the reliability issues brought …

Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications,
spanning from image classification to speech recognition. While providing excellent …

A convolutional neural network has the capacity to learn multiple representation levels and
abstraction in order to provide a better understanding of image data. In addition, a good …

We propose three different methods to determine the optimal number of hidden nodes
based on L 1 regularization for a multilayer perceptron network. The first two methods …

While Graph Neural Networks (GNNs) have demonstrated their efficacy in dealing with non-
Euclidean structural data, they are difficult to be deployed in real applications due to the …

Computing derivatives of tensor expressions, also known as tensor calculus, is a
fundamental task in machine learning. A key concern is the efficiency of evaluating the …

Kolmogorov-Arnold Networks (KANs) have recently emerged as a novel approach to
function approximation, demonstrating remarkable potential in various domains. Despite …

Mixed-signal hardware accelerators for deep learning achieve orders of magnitude better
power efficiency than their digital counterparts. In the ultra-low power consumption regime …