A shape optimization problem of cooling fins for computer parts and integrated circuits is modeled and solved in this paper. The main purpose is to determine the shape of a two-dimensional pin fin, which leads to the maximum amount of removed heat. To do this, the shape optimization problem is defined as maximizing the norm of the Nusselt number distribution at the boundary of the pin fin's con...

Abstract Various works have been proposed to solve expensive multiobjective optimization problems (EMOPs) using surrogate-assisted evolutionary algorithms (SAEAs) in recent decades. However, most existing methods focus on EMOPs with less than 30 decision variables, since a large number of training samples are required build an accurate surrogate model for high-dimensional EMOPs, which is unreal...

In this paper, following a two-stage methodology, the differential quadrature element (DQE) model of a three-story frame structure is updated for the vibration analysis. In the first stage, the mass and stiffness matrices are updated using the experimental natural frequencies. Then, having the updated mass and stiffness matrices, the structural damping matrix is updated to minimize the error be...

—This work addresses the problem of how a robot can improve a manipulation skill in a sample-efficient and secure manner. As an alternative to the standard reinforcement learning formulation where all objectives are defined in a single reward function, we propose a generalized formulation that consists of three components: 1) A known analytic control cost function; 2) A black-box return functio...

Unsupervised kernel regression (UKR), the unsupervised counterpart of the Nadaraya-Watson estimator, is a dimension reduction technique for learning of low-dimensional manifolds. It is based on optimizing representative low-dimensional latent variables with regard to the data space reconstruction error. The problem of scaling initial local linear embedding solutions, and optimization in latent ...