Andrej Karpathy's new open source 'autoresearch' lets you run hundreds of AI experiments a night — with revolutionary implications

An AI agent reads its own source code, forms a hypothesis for improvement (such as changing a learning rate or an architecture depth), modifies the code, runs the experiment, and evaluates the results ...
IEEE

NGnet-Based Sequential Optimization Technique of Variable Flux Memory Machines Considering Multimagnetization State Ripple Suppression

Abstract: Since the existence of multiple magnetization states (MSs), variable flux memory machines (VFMMs) are difficult to optimize, especially their torque ripples under multiple states fail to be ...
IEEE

Sequential Linear Programming With Adaptive Linearization Error Limits for All-Time Feasibility

Abstract: This letter presents an enhanced Trust Region Method (TRM) for Sequential Linear Programming (SLP) designed to improve the initial feasible solution to a constrained nonlinear programming ...
Frontiers

Enhancing Fast Neutron Irradiation in Thermal Neutron Spectrum Reactors Through Python-Based Multi-Objective Optimization

The final, formatted version of the article will be published soon. This work reports on a pilot study for optimizing the design of a fast neutron irradiation experiment in a thermal neutron spectrum, ...