Abstract: Reinforcement Learning is a branch of machine learning to learn control strategies that achieve a given objective through trial-and-error in the environment ...

Abstract: This paper compares the performance of activation function hardware under exponential function approximation techniques. The activation function is a key component of deep neural networks, ...

Approximation theory and asymptotic methods form a foundational framework that bridges classical ideas with modern numerical analysis, enabling researchers to obtain practical, near‐optimal solutions ...

• Artificial Intelligence • In this project we aim to train an artificial neural network to approximate a function of a discrete dynamical system.

Adequate mathematical modeling is the key to success for many real-world projects in engineering, medicine, and other applied areas. Once a well-suited model is established, it can be thoroughly ...

Adaptive Fourier Decomposition and Rational Approximation Techniques represent a significant evolution in the analysis and reconstruction of signals and functions. These methods extend classical ...

1 Warwick Mathematics Institute, The University of Warwick, Coventry, United Kingdom 2 School of Computer and Information Engineering, Luoyang Institute of Science and Technology, Luoyang, China To ...

In their 2001 paper, Longstaff and Schwartz suggested a method for American option pricing using simulation and regression, and since then this method has rapidly gained importance. However, the idea ...

This paper develops a new scheme for improving an approximation method of a probability density function, which is inspired by the idea in the Hilbert space projection theorem. Moreover, we apply ...